X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=81eaddc7260333e70a01be3ea354edfc7513f339;hb=14294236bf9623fac4ad748389689b77d52b3547;hp=64a6cfbc8fa68ef34165eb1881c36ff7edbd2adf;hpb=60bd48b175792d55cc91a3ad8c3109e2ed30fcb8;p=youtube-dl
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 64a6cfbc8..81eaddc72 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -15,6 +15,7 @@ import email.utils
import xml.etree.ElementTree
import random
import math
+import operator
from .utils import *
@@ -47,7 +48,7 @@ class InfoExtractor(object):
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
+ subtitles: The subtitle file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
@@ -73,13 +74,15 @@ class InfoExtractor(object):
self._ready = False
self.set_downloader(downloader)
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
+ return re.match(cls._VALID_URL, url) is not None
- def working(self):
+ @classmethod
+ def working(cls):
"""Getter method for _WORKING."""
- return self._WORKING
+ return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
@@ -123,8 +126,36 @@ class InfoExtractor(object):
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+ content_type = urlh.headers.get('Content-Type', '')
+ m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
+ if m:
+ encoding = m.group(1)
+ else:
+ encoding = 'utf-8'
webpage_bytes = urlh.read()
- return webpage_bytes.decode('utf-8', 'replace')
+ return webpage_bytes.decode(encoding, 'replace')
+
+ #Methods for following #608
+ #They set the correct value of the '_type' key
+ def video_result(self, video_info):
+ """Returns a video"""
+ video_info['_type'] = 'video'
+ return video_info
+ def url_result(self, url, ie=None):
+ """Returns a url that points to a page that should be processed"""
+ #TODO: ie should be the class used for getting the info
+ video_info = {'_type': 'url',
+ 'url': url}
+ return video_info
+ def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+ """Returns a playlist"""
+ video_info = {'_type': 'playlist',
+ 'entries': entries}
+ if playlist_id:
+ video_info['id'] = playlist_id
+ if playlist_title:
+ video_info['title'] = playlist_title
+ return video_info
class YoutubeIE(InfoExtractor):
@@ -136,7 +167,6 @@ class YoutubeIE(InfoExtractor):
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
@@ -188,9 +218,11 @@ class YoutubeIE(InfoExtractor):
}
IE_NAME = u'youtube'
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ if YoutubePlaylistIE.suitable(url): return False
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
@@ -214,7 +246,16 @@ class YoutubeIE(InfoExtractor):
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
+ self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id)
+
+ def report_video_subtitles_request(self, video_id, sub_lang, format):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
+
+ def report_video_subtitles_available(self, video_id, sub_lang_list):
+ """Report available subtitles."""
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self._downloader.to_screen(u'[youtube] %s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
@@ -228,55 +269,75 @@ class YoutubeIE(InfoExtractor):
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected')
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
-
- def _extract_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
- srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- return (u'WARNING: video has no closed captions', None)
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = list(srt_lang_list.keys())[0]
- if not srt_lang in srt_lang_list:
- return (u'WARNING: no closed captions found in the specified language', None)
+ return (u'unable to download video subtitles: %s' % compat_str(err), None)
+ sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+ sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
+ if not sub_lang_list:
+ return (u'video doesn\'t have subtitles', None)
+ return sub_lang_list
+
+ def _list_available_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ self.report_video_subtitles_available(video_id, sub_lang_list)
+
+ def _request_subtitle(self, sub_lang, sub_name, video_id, format):
+ """
+ Return tuple:
+ (error_message, sub_lang, sub)
+ """
+ self.report_video_subtitles_request(video_id, sub_lang, format)
params = compat_urllib_parse.urlencode({
- 'lang': srt_lang,
- 'name': srt_lang_list[srt_lang].encode('utf-8'),
+ 'lang': sub_lang,
+ 'name': sub_name,
'v': video_id,
+ 'fmt': format,
})
url = 'http://www.youtube.com/api/timedtext?' + params
try:
- srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8')
+ sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- if not srt_xml:
- return (u'WARNING: Did not fetch video subtitles', None)
- return (None, self._closed_captions_xml_to_srt(srt_xml))
+ return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
+ if not sub:
+ return (u'Did not fetch video subtitles', None, None)
+ return (None, sub_lang, sub)
+
+ def _extract_subtitle(self, video_id):
+ """
+ Return a list with a tuple:
+ [(error_message, sub_lang, sub)]
+ """
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ if self._downloader.params.get('subtitleslang', False):
+ sub_lang = self._downloader.params.get('subtitleslang')
+ elif 'en' in sub_lang_list:
+ sub_lang = 'en'
+ else:
+ sub_lang = list(sub_lang_list.keys())[0]
+ if not sub_lang in sub_lang_list:
+ return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
+
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ return [subtitle]
+
+ def _extract_all_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ subtitles = []
+ for sub_lang in sub_lang_list:
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ subtitles.append(subtitle)
+ return subtitles
def _print_formats(self, formats):
print('Available formats:')
@@ -304,7 +365,7 @@ class YoutubeIE(InfoExtractor):
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
# Set language
@@ -313,7 +374,7 @@ class YoutubeIE(InfoExtractor):
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
# No authentication to be performed
@@ -324,7 +385,7 @@ class YoutubeIE(InfoExtractor):
try:
login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to fetch login page: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
return
galx = None
@@ -368,10 +429,10 @@ class YoutubeIE(InfoExtractor):
self.report_login()
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
if re.search(r'(?i)]* id="gaia_loginform"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ self._downloader.report_warning(u'unable to log in: bad username or password')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
# Confirm age
@@ -384,13 +445,13 @@ class YoutubeIE(InfoExtractor):
self.report_age_confirmation()
age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err))
return
def _extract_id(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(2)
return video_id
@@ -409,7 +470,7 @@ class YoutubeIE(InfoExtractor):
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
return
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
@@ -434,18 +495,18 @@ class YoutubeIE(InfoExtractor):
if 'token' in video_info:
break
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video info webpage: %s' % compat_str(err))
return
if 'token' not in video_info:
if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
+ self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0])
else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
+ self._downloader.report_error(u'"token" parameter not in video info for unknown reason')
return
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.trouble(u'ERROR: "rental" videos not supported')
+ self._downloader.report_error(u'"rental" videos not supported')
return
# Start extracting information
@@ -453,7 +514,7 @@ class YoutubeIE(InfoExtractor):
# uploader
if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader name')
+ self._downloader.report_error(u'unable to extract uploader name')
return
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
@@ -463,17 +524,17 @@ class YoutubeIE(InfoExtractor):
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ self._downloader.report_warning(u'unable to extract uploader nickname')
# title
if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
@@ -497,15 +558,29 @@ class YoutubeIE(InfoExtractor):
else:
video_description = ''
- # closed captions
+ # subtitles
video_subtitles = None
+
if self._downloader.params.get('writesubtitles', False):
- (srt_error, video_subtitles) = self._extract_subtitles(video_id)
- if srt_error:
- self._downloader.trouble(srt_error)
+ video_subtitles = self._extract_subtitle(video_id)
+ if video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitles[0]
+ if sub_error:
+ self._downloader.report_error(sub_error)
+
+ if self._downloader.params.get('allsubtitles', False):
+ video_subtitles = self._extract_all_subtitles(video_id)
+ for video_subtitle in video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitle
+ if sub_error:
+ self._downloader.report_error(sub_error)
+
+ if self._downloader.params.get('listsubtitles', False):
+ sub_lang_list = self._list_available_subtitles(video_id)
+ return
if 'length_seconds' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video duration')
+ self._downloader.report_warning(u'unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
@@ -533,7 +608,7 @@ class YoutubeIE(InfoExtractor):
format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
+ self._downloader.report_error(u'no known formats available for video')
return
if self._downloader.params.get('listformats', None):
self._print_formats(existing_formats)
@@ -554,10 +629,10 @@ class YoutubeIE(InfoExtractor):
video_url_list = [(rf, url_map[rf])]
break
if video_url_list is None:
- self._downloader.trouble(u'ERROR: requested format not available')
+ self._downloader.report_error(u'requested format not available')
return
else:
- self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
+ self._downloader.report_error(u'no conn or url_encoded_fmt_stream_map information found in video info')
return
results = []
@@ -620,7 +695,7 @@ class MetacafeIE(InfoExtractor):
self.report_disclaimer()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to retrieve disclaimer: %s' % compat_str(err))
return
# Confirm age
@@ -633,14 +708,14 @@ class MetacafeIE(InfoExtractor):
self.report_age_confirmation()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err))
return
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -657,7 +732,7 @@ class MetacafeIE(InfoExtractor):
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable retrieve video webpage: %s' % compat_str(err))
return
# Extract URL, uploader and title from webpage
@@ -677,15 +752,15 @@ class MetacafeIE(InfoExtractor):
else:
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.report_error(u'unable to extract media URL')
return
vardict = compat_parse_qs(mobj.group(1))
if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.report_error(u'unable to extract media URL')
return
mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.report_error(u'unable to extract media URL')
return
mediaURL = mobj.group(1).replace('\\/', '/')
video_extension = mediaURL[-3:]
@@ -693,13 +768,13 @@ class MetacafeIE(InfoExtractor):
mobj = re.search(r'(?im)(.*) - Video', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'submitter=(.*?);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ self._downloader.report_error(u'unable to extract uploader nickname')
return
video_uploader = mobj.group(1)
@@ -731,7 +806,7 @@ class DailymotionIE(InfoExtractor):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1).split('_')[0].split('?')[0]
@@ -747,7 +822,7 @@ class DailymotionIE(InfoExtractor):
self.report_extraction(video_id)
mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.report_error(u'unable to extract media URL')
return
flashvars = compat_urllib_parse.unquote(mobj.group(1))
@@ -757,12 +832,12 @@ class DailymotionIE(InfoExtractor):
self._downloader.to_screen(u'[dailymotion] Using %s' % key)
break
else:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
+ self._downloader.report_error(u'unable to extract video URL')
return
mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
+ self._downloader.report_error(u'unable to extract video URL')
return
video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
@@ -771,7 +846,7 @@ class DailymotionIE(InfoExtractor):
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_title = unescapeHTML(mobj.group('title'))
@@ -781,7 +856,7 @@ class DailymotionIE(InfoExtractor):
# lookin for official user
mobj_official = re.search(r']+?>([^<]+?)', webpage)
if mobj_official is None:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ self._downloader.report_warning(u'unable to extract uploader nickname')
else:
video_uploader = mobj_official.group(1)
else:
@@ -823,7 +898,7 @@ class PhotobucketIE(InfoExtractor):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -836,14 +911,14 @@ class PhotobucketIE(InfoExtractor):
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.report_error(u'unable to extract media URL')
return
mediaURL = compat_urllib_parse.unquote(mobj.group(1))
@@ -851,7 +926,7 @@ class PhotobucketIE(InfoExtractor):
mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
@@ -892,7 +967,7 @@ class YahooIE(InfoExtractor):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
video_id = mobj.group(2)
@@ -905,18 +980,18 @@ class YahooIE(InfoExtractor):
try:
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
+ self._downloader.report_error(u'Unable to extract id field')
return
yahoo_id = mobj.group(1)
mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
+ self._downloader.report_error(u'Unable to extract vid field')
return
yahoo_vid = mobj.group(1)
@@ -929,34 +1004,34 @@ class YahooIE(InfoExtractor):
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
# Extract uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ self._downloader.report_error(u'unable to extract video uploader')
return
video_uploader = mobj.group(1).decode('utf-8')
# Extract video thumbnail
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ self._downloader.report_error(u'unable to extract video thumbnail')
return
video_thumbnail = mobj.group(1).decode('utf-8')
# Extract video description
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
+ self._downloader.report_error(u'unable to extract video description')
return
video_description = mobj.group(1).decode('utf-8')
if not video_description:
@@ -965,13 +1040,13 @@ class YahooIE(InfoExtractor):
# Extract video height and width
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
+ self._downloader.report_error(u'unable to extract video height')
return
yv_video_height = mobj.group(1)
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
+ self._downloader.report_error(u'unable to extract video width')
return
yv_video_width = mobj.group(1)
@@ -987,13 +1062,13 @@ class YahooIE(InfoExtractor):
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
# Extract media URL from playlist XML
mobj = re.search(r'(.*)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_title = mobj.group(1)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_uploader = mobj.group(1)
@@ -1433,7 +1504,7 @@ class YoutubeSearchIE(InfoExtractor):
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ self._downloader.report_error(u'invalid search query "%s"' % query)
return
prefix, query = query.split(':')
@@ -1449,10 +1520,10 @@ class YoutubeSearchIE(InfoExtractor):
try:
n = int(prefix)
if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
self._download_n_results(query, n)
return
@@ -1472,12 +1543,16 @@ class YoutubeSearchIE(InfoExtractor):
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
request = compat_urllib_request.Request(result_url)
try:
- data = compat_urllib_request.urlopen(request).read()
+ data = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download API page: %s' % compat_str(err))
return
api_response = json.loads(data)['data']
+ if not 'items' in api_response:
+ self._downloader.trouble(u'[youtube] No video results')
+ return
+
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
@@ -1511,7 +1586,7 @@ class GoogleSearchIE(InfoExtractor):
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ self._downloader.report_error(u'invalid search query "%s"' % query)
return
prefix, query = query.split(':')
@@ -1527,10 +1602,10 @@ class GoogleSearchIE(InfoExtractor):
try:
n = int(prefix)
if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
n = self._max_google_results
self._download_n_results(query, n)
return
@@ -1551,7 +1626,7 @@ class GoogleSearchIE(InfoExtractor):
try:
page = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
# Extract video identifiers
@@ -1595,7 +1670,7 @@ class YahooSearchIE(InfoExtractor):
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ self._downloader.report_error(u'invalid search query "%s"' % query)
return
prefix, query = query.split(':')
@@ -1611,10 +1686,10 @@ class YahooSearchIE(InfoExtractor):
try:
n = int(prefix)
if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
n = self._max_yahoo_results
self._download_n_results(query, n)
return
@@ -1636,7 +1711,7 @@ class YahooSearchIE(InfoExtractor):
try:
page = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
# Extract video identifiers
@@ -1662,81 +1737,92 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
+ _VALID_URL = r"""(?:
+ (?:https?://)?
+ (?:\w+\.)?
+ youtube\.com/
+ (?:
+ (?:course|view_play_list|my_playlists|artist|playlist|watch)
+ \? (?:.*?&)*? (?:p|a|list)=
+ | p/
+ )
+ ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
+ .*
+ |
+ ((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
+ )"""
+ _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
+ _MAX_RESULTS = 50
IE_NAME = u'youtube:playlist'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number."""
self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
def _real_extract(self, url):
# Extract playlist id
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ self._downloader.report_error(u'invalid url: %s' % url)
return
- # Single video case
- if mobj.group(3) is not None:
- self._downloader.download([mobj.group(3)])
- return
-
- # Download playlist pages
- # prefix is 'p' as default for playlists but there are other types that need extra care
- playlist_prefix = mobj.group(1)
- if playlist_prefix == 'a':
- playlist_access = 'artist'
- else:
- playlist_prefix = 'p'
- playlist_access = 'view_play_list'
- playlist_id = mobj.group(2)
- video_ids = []
- pagenum = 1
+ # Download playlist videos from API
+ playlist_id = mobj.group(1) or mobj.group(2)
+ page_num = 1
+ videos = []
while True:
- self.report_download_page(playlist_id, pagenum)
- url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
- request = compat_urllib_request.Request(url)
+ self.report_download_page(playlist_id, page_num)
+
+ url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ page = compat_urllib_request.urlopen(url).read().decode('utf8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ try:
+ response = json.loads(page)
+ except ValueError as err:
+ self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err))
+ return
- if self._MORE_PAGES_INDICATOR not in page:
+ if not 'feed' in response or not 'entry' in response['feed']:
+ self._downloader.report_error(u'Got a malformed response from YouTube API')
+ return
+ videos += [ (entry['yt$position']['$t'], entry['content']['src'])
+ for entry in response['feed']['entry']
+ if 'content' in entry ]
+
+ if len(response['feed']['entry']) < self._MAX_RESULTS:
break
- pagenum = pagenum + 1
+ page_num += 1
- total = len(video_ids)
+ videos = [v[1] for v in sorted(videos)]
+ total = len(videos)
playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1)
if playlistend == -1:
- video_ids = video_ids[playliststart:]
+ videos = videos[playliststart:]
else:
- video_ids = video_ids[playliststart:playlistend]
+ videos = videos[playliststart:playlistend]
- if len(video_ids) == total:
+ if len(videos) == total:
self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
else:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids)))
+ self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(videos)))
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ url_results = [self.url_result(url) for url in videos]
+ return [self.playlist_result(url_results, playlist_id)]
class YoutubeChannelIE(InfoExtractor):
@@ -1755,7 +1841,7 @@ class YoutubeChannelIE(InfoExtractor):
# Extract channel id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ self._downloader.report_error(u'invalid url: %s' % url)
return
# Download channel pages
@@ -1770,7 +1856,7 @@ class YoutubeChannelIE(InfoExtractor):
try:
page = compat_urllib_request.urlopen(request).read().decode('utf8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
# Extract video identifiers
@@ -1786,9 +1872,9 @@ class YoutubeChannelIE(InfoExtractor):
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
+ url_entries = [self.url_result(url) for url in urls]
+ return [self.playlist_result(url_entries, channel_id)]
class YoutubeUserIE(InfoExtractor):
@@ -1813,7 +1899,7 @@ class YoutubeUserIE(InfoExtractor):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ self._downloader.report_error(u'invalid url: %s' % url)
return
username = mobj.group(1)
@@ -1835,7 +1921,7 @@ class YoutubeUserIE(InfoExtractor):
try:
page = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
# Extract video identifiers
@@ -1870,8 +1956,9 @@ class YoutubeUserIE(InfoExtractor):
self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
(username, all_ids_count, len(video_ids)))
- for video_id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
+ urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
+ url_results = [self.url_result(url) for url in urls]
+ return [self.playlist_result(url_results, playlist_title = username)]
class BlipTVUserIE(InfoExtractor):
@@ -1893,7 +1980,7 @@ class BlipTVUserIE(InfoExtractor):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ self._downloader.report_error(u'invalid url: %s' % url)
return
username = mobj.group(1)
@@ -1907,7 +1994,7 @@ class BlipTVUserIE(InfoExtractor):
mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
@@ -1921,13 +2008,12 @@ class BlipTVUserIE(InfoExtractor):
while True:
self.report_download_page(username, pagenum)
-
- request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
-
+ url = page_base + "&page=" + str(pagenum)
+ request = compat_urllib_request.Request( url )
try:
page = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % str(err))
return
# Extract video identifiers
@@ -1962,8 +2048,9 @@ class BlipTVUserIE(InfoExtractor):
self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
(self.IE_NAME, username, all_ids_count, len(video_ids)))
- for video_id in video_ids:
- self._downloader.download([u'http://blip.tv/'+video_id])
+ urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
+ url_entries = [self.url_result(url) for url in urls]
+ return [self.playlist_result(url_entries, playlist_title = username)]
class DepositFilesIE(InfoExtractor):
@@ -1991,7 +2078,7 @@ class DepositFilesIE(InfoExtractor):
self.report_download_webpage(file_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve file webpage: %s' % compat_str(err))
return
# Search for the real file URL
@@ -2001,9 +2088,9 @@ class DepositFilesIE(InfoExtractor):
mobj = re.search(r'(Attention.*?)', webpage, re.DOTALL)
if (mobj is not None) and (mobj.group(1) is not None):
restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
- self._downloader.trouble(u'ERROR: %s' % restriction_message)
+ self._downloader.report_error(u'%s' % restriction_message)
else:
- self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
+ self._downloader.report_error(u'unable to extract download URL from: %s' % url)
return
file_url = mobj.group(1)
@@ -2012,7 +2099,7 @@ class DepositFilesIE(InfoExtractor):
# Search for file title
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
file_title = mobj.group(1).decode('utf-8')
@@ -2059,7 +2146,7 @@ class FacebookIE(InfoExtractor):
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
if useremail is None:
@@ -2076,16 +2163,16 @@ class FacebookIE(InfoExtractor):
self.report_login()
login_results = compat_urllib_request.urlopen(request).read()
if re.search(r'', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+ self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('ID')
@@ -2141,9 +2228,20 @@ class BlipTVIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
+ urlp = compat_urllib_parse_urlparse(url)
+ if urlp.path.startswith('/play/'):
+ request = compat_urllib_request.Request(url)
+ response = compat_urllib_request.urlopen(request)
+ redirecturl = response.geturl()
+ rurlp = compat_urllib_parse_urlparse(redirecturl)
+ file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
+ url = 'http://blip.tv/a/a-' + file_id
+ return self._real_extract(url)
+
+
if '?' in url:
cchar = '&'
else:
@@ -2177,7 +2275,7 @@ class BlipTVIE(InfoExtractor):
json_code_bytes = urlh.read()
json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to read video info webpage: %s' % compat_str(err))
return
try:
@@ -2208,7 +2306,7 @@ class BlipTVIE(InfoExtractor):
'user_agent': 'iTunes/10.6.1',
}
except (ValueError,KeyError) as err:
- self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+ self._downloader.report_error(u'unable to parse video information: %s' % repr(err))
return
return [info]
@@ -2230,7 +2328,7 @@ class MyVideoIE(InfoExtractor):
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._download.trouble(u'ERROR: invalid URL: %s' % url)
+ self._download.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -2240,16 +2338,16 @@ class MyVideoIE(InfoExtractor):
webpage = self._download_webpage(webpage_url, video_id)
self.report_extraction(video_id)
- mobj = re.search(r'',
+ mobj = re.search(r'([^<]+)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
video_title = mobj.group(1)
@@ -2299,9 +2397,10 @@ class ComedyCentralIE(InfoExtractor):
'400': '384x216',
}
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@@ -2321,7 +2420,7 @@ class ComedyCentralIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
if mobj.group('shortname'):
@@ -2352,16 +2451,16 @@ class ComedyCentralIE(InfoExtractor):
html = htmlHandle.read()
webpage = html.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+ self._downloader.report_error(u'Invalid redirected URL: ' + url)
return
if mobj.group('episode') == '':
- self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+ self._downloader.report_error(u'Redirected URL is still not specific: ' + url)
return
epTitle = mobj.group('episode')
@@ -2374,7 +2473,7 @@ class ComedyCentralIE(InfoExtractor):
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
- self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ self._downloader.report_error(u'unable to find Flash URL in webpage ' + url)
return
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
@@ -2385,7 +2484,7 @@ class ComedyCentralIE(InfoExtractor):
try:
indexXml = compat_urllib_request.urlopen(indexUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err))
+ self._downloader.report_error(u'unable to download episode index: ' + compat_str(err))
return
results = []
@@ -2406,7 +2505,7 @@ class ComedyCentralIE(InfoExtractor):
try:
configXml = compat_urllib_request.urlopen(configReq).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
return
cdoc = xml.etree.ElementTree.fromstring(configXml)
@@ -2416,7 +2515,7 @@ class ComedyCentralIE(InfoExtractor):
turls.append(finfo)
if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+ self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
continue
if self._downloader.params.get('listformats', None):
@@ -2473,7 +2572,7 @@ class EscapistIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
showName = mobj.group('showname')
videoId = mobj.group('episode')
@@ -2485,7 +2584,7 @@ class EscapistIE(InfoExtractor):
m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err))
+ self._downloader.report_error(u'unable to download webpage: ' + compat_str(err))
return
descMatch = re.search('(.*?)\s+-\s+XVID', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
video_title = mobj.group(1)
@@ -2645,7 +2744,7 @@ class XVideosIE(InfoExtractor):
# Extract video thumbnail
mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ self._downloader.report_error(u'unable to extract video thumbnail')
return
video_thumbnail = mobj.group(0)
@@ -2689,7 +2788,7 @@ class SoundcloudIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
# extract uploader (which is in the url)
@@ -2707,7 +2806,7 @@ class SoundcloudIE(InfoExtractor):
info_json_bytes = compat_urllib_request.urlopen(request).read()
info_json = info_json_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
return
info = json.loads(info_json)
@@ -2720,7 +2819,7 @@ class SoundcloudIE(InfoExtractor):
stream_json_bytes = compat_urllib_request.urlopen(request).read()
stream_json = stream_json_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err))
return
streams = json.loads(stream_json)
@@ -2736,6 +2835,87 @@ class SoundcloudIE(InfoExtractor):
'description': info['description'],
}]
+class SoundcloudSetIE(InfoExtractor):
+ """Information extractor for soundcloud.com sets
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+ IE_NAME = u'soundcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_resolve(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1)
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2)
+ simple_title = uploader + u'-' + slug_title
+
+ self.report_resolve('%s/sets/%s' % (uploader, slug_title))
+
+ url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
+ resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(resolv_url)
+ try:
+ info_json_bytes = compat_urllib_request.urlopen(request).read()
+ info_json = info_json_bytes.decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ return
+
+ videos = []
+ info = json.loads(info_json)
+ if 'errors' in info:
+ for err in info['errors']:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err['error_message']))
+ return
+
+ for track in info['tracks']:
+ video_id = track['id']
+ self.report_extraction('%s/sets/%s' % (uploader, slug_title))
+
+ streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(streams_url)
+ try:
+ stream_json_bytes = compat_urllib_request.urlopen(request).read()
+ stream_json = stream_json_bytes.decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
+ return
+
+ streams = json.loads(stream_json)
+ mediaURL = streams['http_mp3_128_url']
+
+ videos.append({
+ 'id': video_id,
+ 'url': mediaURL,
+ 'uploader': track['user']['username'],
+ 'upload_date': track['created_at'],
+ 'title': track['title'],
+ 'ext': u'mp3',
+ 'description': track['description'],
+ })
+ return videos
+
class InfoQIE(InfoExtractor):
"""Information extractor for infoq.com"""
@@ -2748,7 +2928,7 @@ class InfoQIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
webpage = self._download_webpage(url, video_id=url)
@@ -2757,7 +2937,7 @@ class InfoQIE(InfoExtractor):
# Extract video URL
mobj = re.search(r"jsclassref='([^']*)'", webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
+ self._downloader.report_error(u'unable to extract video url')
return
real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
@@ -2765,7 +2945,7 @@ class InfoQIE(InfoExtractor):
# Extract title
mobj = re.search(r'contentTitle = "(.*?)";', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
video_title = mobj.group(1)
@@ -2848,7 +3028,7 @@ class MixcloudIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
# extract uploader & filename from url
uploader = mobj.group(1).decode('utf-8')
@@ -2862,7 +3042,7 @@ class MixcloudIE(InfoExtractor):
self.report_download_json(file_url)
jsonData = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve file: %s' % compat_str(err))
return
# parse JSON
@@ -2886,7 +3066,7 @@ class MixcloudIE(InfoExtractor):
break # got it!
else:
if req_format not in formats:
- self._downloader.trouble(u'ERROR: format is not available')
+ self._downloader.report_error(u'format is not available')
return
url_list = self.get_urls(formats, req_format)
@@ -2940,14 +3120,14 @@ class StanfordOpenClassroomIE(InfoExtractor):
try:
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err))
return
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
info['title'] = mdoc.findall('./title')[0].text
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ self._downloader.report_error(u'Invalid metadata XML file')
return
info['ext'] = info['url'].rpartition('.')[2]
return [info]
@@ -2999,7 +3179,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
try:
rootpage = compat_urllib_request.urlopen(rootURL).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
+ self._downloader.report_error(u'unable to download course info page: ' + compat_str(err))
return
info['title'] = info['id']
@@ -3031,7 +3211,7 @@ class MTVIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
if not mobj.group('proto'):
url = 'http://' + url
@@ -3041,25 +3221,25 @@ class MTVIE(InfoExtractor):
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract song name')
+ self._downloader.report_error(u'unable to extract song name')
return
song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract performer')
+ self._downloader.report_error(u'unable to extract performer')
return
performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
video_title = performer + ' - ' + song_name
mobj = re.search(r'', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to mtvn_uri')
+ self._downloader.report_error(u'unable to mtvn_uri')
return
mtvn_uri = mobj.group(1)
mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract content id')
+ self._downloader.report_error(u'unable to extract content id')
return
content_id = mobj.group(1)
@@ -3069,7 +3249,7 @@ class MTVIE(InfoExtractor):
try:
metadataXml = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video metadata: %s' % compat_str(err))
return
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
@@ -3141,7 +3321,7 @@ class YoukuIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('ID')
@@ -3152,7 +3332,7 @@ class YoukuIE(InfoExtractor):
self.report_download_webpage(video_id)
jsondata = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
self.report_extraction(video_id)
@@ -3183,7 +3363,7 @@ class YoukuIE(InfoExtractor):
fileid = config['data'][0]['streamfileids'][format]
keys = [s['k'] for s in config['data'][0]['segs'][format]]
except (UnicodeDecodeError, ValueError, KeyError):
- self._downloader.trouble(u'ERROR: unable to extract info section')
+ self._downloader.report_error(u'unable to extract info section')
return
files_info=[]
@@ -3230,7 +3410,7 @@ class XNXXIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -3241,24 +3421,24 @@ class XNXXIE(InfoExtractor):
webpage_bytes = compat_urllib_request.urlopen(url).read()
webpage = webpage_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
+ self._downloader.report_error(u'unable to download video webpage: %s' % err)
return
result = re.search(self.VIDEO_URL_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
+ self._downloader.report_error(u'unable to extract video url')
return
video_url = compat_urllib_parse.unquote(result.group(1))
result = re.search(self.VIDEO_TITLE_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
video_title = result.group(1)
result = re.search(self.VIDEO_THUMB_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ self._downloader.report_error(u'unable to extract video thumbnail')
return
video_thumbnail = result.group(1)
@@ -3307,7 +3487,7 @@ class GooglePlusIE(InfoExtractor):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
post_url = mobj.group(0)
@@ -3321,7 +3501,7 @@ class GooglePlusIE(InfoExtractor):
try:
webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve entry webpage: %s' % compat_str(err))
return
# Extract update date
@@ -3356,14 +3536,14 @@ class GooglePlusIE(InfoExtractor):
pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
mobj = re.search(pattern, webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video page URL')
+ self._downloader.report_error(u'unable to extract video page URL')
video_page = mobj.group(1)
request = compat_urllib_request.Request(video_page)
try:
webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
return
self.report_extract_vid_page(video_page)
@@ -3373,7 +3553,7 @@ class GooglePlusIE(InfoExtractor):
pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
mobj = re.findall(pattern, webpage)
if len(mobj) == 0:
- self._downloader.trouble(u'ERROR: unable to extract video links')
+ self._downloader.report_error(u'unable to extract video links')
# Sort in resolution
links = sorted(mobj)
@@ -3405,7 +3585,7 @@ class NBAIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -3461,13 +3641,13 @@ class JustinTVIE(InfoExtractor):
webpage_bytes = urlh.read()
webpage = webpage_bytes.decode('utf-8', 'ignore')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info JSON: %s' % compat_str(err))
+ self._downloader.report_error(u'unable to download video info JSON: %s' % compat_str(err))
return
response = json.loads(webpage)
if type(response) != list:
error_text = response.get('error', 'unknown error')
- self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
+ self._downloader.report_error(u'Justin.tv API: %s' % error_text)
return
info = []
for clip in response:
@@ -3492,7 +3672,7 @@ class JustinTVIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
api = 'http://api.justin.tv'
@@ -3527,7 +3707,7 @@ class FunnyOrDieIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('id')
@@ -3535,13 +3715,13 @@ class FunnyOrDieIE(InfoExtractor):
m = re.search(r']*>\s*]*>\s*\s+(?P.*?)</a>", webpage)
+ m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
if not m:
self._downloader.trouble(u'Cannot find video title')
- title = unescapeHTML(m.group('title'))
+ title = clean_html(m.group('title'))
m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
if m:
@@ -3558,65 +3738,17 @@ class FunnyOrDieIE(InfoExtractor):
}
return [info]
-class TweetReelIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
-
- m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage)
- if not m:
- self._downloader.trouble(u'ERROR: Cannot find status ID')
- status_id = m.group(1)
-
- m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL)
- if not m:
- self._downloader.trouble(u'WARNING: Cannot find description')
- desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip()
-
- m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL)
- if not m:
- self._downloader.trouble(u'ERROR: Cannot find uploader')
- uploader = unescapeHTML(m.group('uploader'))
- uploader_id = unescapeHTML(m.group('uploader_id'))
-
- m = re.search(r'<span unixtime="([0-9]+)"', webpage)
- if not m:
- self._downloader.trouble(u'ERROR: Cannot find upload date')
- upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d')
-
- title = desc
- video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov'
-
- info = {
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mov',
- 'title': title,
- 'description': desc,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'internal_id': status_id,
- 'upload_date': upload_date
- }
- return [info]
-
class SteamIE(InfoExtractor):
- _VALID_URL = r"""http://store.steampowered.com/
+ _VALID_URL = r"""http://store.steampowered.com/
(?P<urltype>video|app)/ #If the page is only for videos or for a game
(?P<gameID>\d+)/?
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
"""
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE)
@@ -3636,7 +3768,7 @@ class SteamIE(InfoExtractor):
video_url = vid.group('videoURL')
video_thumb = thumb.group('thumbnail')
if not video_url:
- self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+ self._downloader.report_error(u'Cannot find video url for %s' % video_id)
info = {
'id':video_id,
'url':video_url,
@@ -3669,6 +3801,62 @@ class UstreamIE(InfoExtractor):
}
return [info]
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ IE_NAME = u'WorldStarHipHop'
+
+ def _real_extract(self, url):
+ _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
+
+ webpage_src = compat_urllib_request.urlopen(url).read()
+ webpage_src = webpage_src.decode('utf-8')
+
+ mobj = re.search(_src_url, webpage_src)
+
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ if mobj is not None:
+ video_url = mobj.group()
+ if 'mp4' in video_url:
+ ext = 'mp4'
+ else:
+ ext = 'flv'
+ else:
+ self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+ return
+
+ _title = r"""<title>(.*)"""
+
+ mobj = re.search(_title, webpage_src)
+
+ if mobj is not None:
+ title = mobj.group(1)
+ else:
+ title = 'World Start Hip Hop - %s' % time.ctime()
+
+ _thumbnail = r"""rel="image_src" href="(.*)" />"""
+ mobj = re.search(_thumbnail, webpage_src)
+
+ # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+ if mobj is not None:
+ thumbnail = mobj.group(1)
+ else:
+ _title = r"""candytitles.*>(.*)"""
+ mobj = re.search(_title, webpage_src)
+ if mobj is not None:
+ title = mobj.group(1)
+ thumbnail = None
+
+ results = [{
+ 'id': video_id,
+ 'url' : video_url,
+ 'title' : title,
+ 'thumbnail' : thumbnail,
+ 'ext' : ext,
+ }]
+ return results
+
class RBMARadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P[^/]+)$'
@@ -3708,7 +3896,7 @@ class RBMARadioIE(InfoExtractor):
class YouPornIE(InfoExtractor):
"""Information extractor for youporn.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P[0-9]+)/(?P[^/]+)'
-
+
def _print_formats(self, formats):
"""Print all available formats"""
print(u'Available formats:')
@@ -3726,7 +3914,7 @@ class YouPornIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('videoid')
@@ -3744,7 +3932,7 @@ class YouPornIE(InfoExtractor):
# Get the video date
result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
if result is None:
- self._downloader.to_stderr(u'WARNING: unable to extract video date')
+ self._downloader.report_warning(u'unable to extract video date')
upload_date = None
else:
upload_date = result.group('date').strip()
@@ -3752,7 +3940,7 @@ class YouPornIE(InfoExtractor):
# Get the video uploader
result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
if result is None:
- self._downloader.to_stderr(u'WARNING: unable to extract uploader')
+ self._downloader.report_warning(u'unable to extract uploader')
video_uploader = None
else:
video_uploader = result.group('uploader').strip()
@@ -3770,8 +3958,8 @@ class YouPornIE(InfoExtractor):
links = re.findall(LINK_RE, download_list_html)
if(len(links) == 0):
raise ExtractorError(u'ERROR: no known formats available for video')
-
- self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))
+
+ self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))
formats = []
for link in links:
@@ -3818,11 +4006,11 @@ class YouPornIE(InfoExtractor):
else:
format = self._specific( req_format, formats )
if result is None:
- self._downloader.trouble(u'ERROR: requested format not available')
+ self._downloader.report_error(u'requested format not available')
return
return [format]
-
+
class PornotubeIE(InfoExtractor):
"""Information extractor for pornotube.com."""
@@ -3831,7 +4019,7 @@ class PornotubeIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('videoid')
@@ -3844,7 +4032,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
result = re.search(VIDEO_URL_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
+ self._downloader.report_error(u'unable to extract video url')
return
video_url = compat_urllib_parse.unquote(result.group('url'))
@@ -3852,7 +4040,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
result = re.search(VIDEO_UPLOADED_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ self._downloader.report_error(u'unable to extract video title')
return
upload_date = result.group('date')
@@ -3873,7 +4061,7 @@ class YouJizzIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group('videoid')
@@ -3894,7 +4082,7 @@ class YouJizzIE(InfoExtractor):
embed_page_url = result.group(0).strip()
video_id = result.group('videoid')
-
+
webpage = self._download_webpage(embed_page_url, video_id)
# Get the video URL
@@ -3968,11 +4156,11 @@ class KeekIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
m = re.search(r'<meta property="og:title" content="(?P<title>.+)"', webpage)
title = unescapeHTML(m.group('title'))
- m = re.search(r'<div class="bio-names-and-report">[\s\n]+<h4>(?P<uploader>\w+)</h4>', webpage)
- uploader = unescapeHTML(m.group('uploader'))
+ m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
+ uploader = clean_html(m.group('uploader'))
info = {
- 'id':video_id,
- 'url':video_url,
+ 'id': video_id,
+ 'url': video_url,
'ext': 'mp4',
'title': title,
'thumbnail': thumbnail,
@@ -3990,9 +4178,10 @@ class TEDIE(InfoExtractor):
/(?P<name>\w+) # Here goes the name and then ".html"
'''
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url):
m=re.match(self._VALID_URL, url, re.VERBOSE)
@@ -4015,31 +4204,30 @@ class TEDIE(InfoExtractor):
([.\s]*?)data-playlist_item_id="(\d+)"
([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
'''
- video_name_RE=r'<p\ class="talk-title"><a href="/talks/(.+).html">(?P<fullname>.+?)</a></p>'
+ video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
m_names=re.finditer(video_name_RE,webpage)
info=[]
for m_video, m_name in zip(m_videos,m_names):
- video_dic={
- 'id': m_video.group('video_id'),
- 'url': self._talk_video_link(m_video.group('mediaSlug')),
- 'ext': 'mp4',
- 'title': m_name.group('fullname')
- }
- info.append(video_dic)
+ video_id=m_video.group('video_id')
+ talk_url='http://www.ted.com%s' % m_name.group('talk_url')
+ info.append(self._talk_info(talk_url,video_id))
return info
+
def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url"""
m=re.match(self._VALID_URL, url,re.VERBOSE)
videoName=m.group('name')
webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
# If the url includes the language we get the title translated
- title_RE=r'<h1><span id="altHeadline" >(?P<title>[\s\w:/\.\?=\+-\\\']*)</span></h1>'
+ title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
title=re.search(title_RE, webpage).group('title')
info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
"id":(?P<videoID>[\d]+).*?
"mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
+ thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
+ thumb_match=re.search(thumb_RE,webpage)
info_match=re.search(info_RE,webpage,re.VERBOSE)
video_id=info_match.group('videoID')
mediaSlug=info_match.group('mediaSlug')
@@ -4048,13 +4236,14 @@ class TEDIE(InfoExtractor):
'id': video_id,
'url': video_url,
'ext': 'mp4',
- 'title': title
+ 'title': title,
+ 'thumbnail': thumb_match.group('thumbnail')
}
return info
class MySpassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
-
+
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
@@ -4064,22 +4253,22 @@ class MySpassIE(InfoExtractor):
url_parent_path, video_id = os.path.split(url_path)
if not video_id:
_, video_id = os.path.split(url_parent_path)
-
+
# get metadata
metadata_url = META_DATA_URL_TEMPLATE % video_id
metadata_text = self._download_webpage(metadata_url, video_id)
metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
-
+
# extract values from metadata
url_flv_el = metadata.find('url_flv')
if url_flv_el is None:
- self._downloader.trouble(u'ERROR: unable to extract download url')
+ self._downloader.report_error(u'unable to extract download url')
return
video_url = url_flv_el.text
extension = os.path.splitext(video_url)[1][1:]
title_el = metadata.find('title')
if title_el is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.report_error(u'unable to extract title')
return
title = title_el.text
format_id_el = metadata.find('format_id')
@@ -4108,6 +4297,89 @@ class MySpassIE(InfoExtractor):
}
return [info]
+class SpiegelIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title')
+ video_title = unescapeHTML(m.group(1))
+
+ xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+ xml_code = self._download_webpage(xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
+
+ idoc = xml.etree.ElementTree.fromstring(xml_code)
+ last_type = idoc[-1]
+ filename = last_type.findall('./filename')[0].text
+ duration = float(last_type.findall('./duration')[0].text)
+
+ video_url = 'http://video2.spiegel.de/flash/' + filename
+ video_ext = filename.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': video_title,
+ 'duration': duration,
+ }
+ return [info]
+
+class LiveLeakIE(InfoExtractor):
+
+ _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ IE_NAME = u'liveleak'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'file: "(.*?)",', webpage)
+ if not m:
+ self._downloader.report_error(u'unable to find video url')
+ return
+ video_url = m.group(1)
+
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ if not m:
+ self._downloader.trouble(u'Cannot find video title')
+ title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ m = re.search(r'By:.*?(\w+)</a>', webpage)
+ if m:
+ uploader = clean_html(m.group(1))
+ else:
+ uploader = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ 'uploader': uploader
+ }
+
+ return [info]
+
+
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
@@ -4134,6 +4406,7 @@ def gen_extractors():
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
+ SoundcloudSetIE(),
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
@@ -4147,9 +4420,9 @@ def gen_extractors():
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
+ WorldStarHipHopIE(),
JustinTVIE(),
FunnyOrDieIE(),
- TweetReelIE(),
SteamIE(),
UstreamIE(),
RBMARadioIE(),
@@ -4157,7 +4430,7 @@ def gen_extractors():
KeekIE(),
TEDIE(),
MySpassIE(),
+ SpiegelIE(),
+ LiveLeakIE(),
GenericIE()
]
-
-