X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=53d65c02eea034f8ea7d2ffe270c9586910aa504;hb=a3d689cfb3b8d6320104bb70725679bc2d336f77;hp=dd4a776e4a50adf7e71ab4580bbbc2fcac81e65d;hpb=cfa90f4adce8b5e7faf92d0a08abe38630b150b8;p=youtube-dl
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index dd4a776e4..53d65c02e 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -115,7 +115,8 @@ class InfoExtractor(object):
""" Returns the response handle """
if note is None:
note = u'Downloading video webpage'
- self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
+ if note is not False:
+ self.to_screen(u'%s: %s' % (video_id, note))
try:
return compat_urllib_request.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@@ -133,8 +134,28 @@ class InfoExtractor(object):
else:
encoding = 'utf-8'
webpage_bytes = urlh.read()
+ if self._downloader.params.get('dump_intermediate_pages', False):
+ try:
+ url = url_or_request.get_full_url()
+ except AttributeError:
+ url = url_or_request
+ self.to_screen(u'Dumping request to ' + url)
+ dump = base64.b64encode(webpage_bytes).decode('ascii')
+ self._downloader.to_screen(dump)
return webpage_bytes.decode(encoding, 'replace')
-
+
+ def to_screen(self, msg):
+ """Print msg to screen, prefixing it with '[ie_name]'"""
+ self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+
+ def report_extraction(self, id_or_name):
+ """Report information extraction."""
+ self.to_screen(u'%s: Extracting information' % id_or_name)
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self.to_screen(u'Confirming age')
+
#Methods for following #608
#They set the correct value of the '_type' key
def video_result(self, video_info):
@@ -145,12 +166,17 @@ class InfoExtractor(object):
"""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}
+ 'url': url,
+ 'ie_key': ie}
return video_info
- def playlist_result(self, entries):
+ 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
@@ -222,48 +248,44 @@ class YoutubeIE(InfoExtractor):
def report_lang(self):
"""Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
+ self.to_screen(u'Setting language')
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
+ self.to_screen(u'Logging in')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
+ self.to_screen(u'%s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+ self.to_screen(u'%s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id)
+ self.to_screen(u'%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))
+ self.to_screen(u'%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))
+ self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
+ self.to_screen(u'%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+ self.to_screen(u'%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
+ self.to_screen(u'RTMP download detected')
def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
@@ -271,11 +293,11 @@ class YoutubeIE(InfoExtractor):
try:
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)
+ 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'WARNING: video doesn\'t have subtitles', None)
+ return (u'video doesn\'t have subtitles', None)
return sub_lang_list
def _list_available_subtitles(self, video_id):
@@ -283,6 +305,10 @@ class YoutubeIE(InfoExtractor):
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': sub_lang,
@@ -294,14 +320,20 @@ class YoutubeIE(InfoExtractor):
try:
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)
+ return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
if not sub:
- return (u'WARNING: Did not fetch video subtitles', None)
+ 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:
@@ -309,7 +341,7 @@ class YoutubeIE(InfoExtractor):
else:
sub_lang = list(sub_lang_list.keys())[0]
if not sub_lang in sub_lang_list:
- return (u'WARNING: no closed captions found in the specified language "%s"' % sub_lang, None)
+ 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]
@@ -317,6 +349,8 @@ class YoutubeIE(InfoExtractor):
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)
@@ -429,13 +463,13 @@ 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
@@ -454,7 +488,7 @@ 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')
@@ -469,28 +503,24 @@ class YoutubeIE(InfoExtractor):
# Get video info
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type))
- request = compat_urllib_request.Request(video_info_url)
- try:
- video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
- video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
- video_info = compat_parse_qs(video_info_webpage)
- 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))
- return
+ video_info_webpage = self._download_webpage(video_info_url, video_id,
+ note=False,
+ errnote='unable to download video info webpage')
+ video_info = compat_parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
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
@@ -498,7 +528,7 @@ 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])
@@ -508,17 +538,17 @@ 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])
@@ -540,7 +570,11 @@ class YoutubeIE(InfoExtractor):
if video_description:
video_description = clean_html(video_description)
else:
- video_description = ''
+ fd_mobj = re.search(r' http.*?)",(.*?)"key":"(?P.*?)"', 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('\\/', '/')
+ mediaURL = mobj.group('mediaURL').replace('\\/', '/')
video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
+ video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
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)
@@ -782,15 +798,11 @@ class DailymotionIE(InfoExtractor):
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
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).split('_')[0].split('?')[0]
@@ -806,22 +818,22 @@ 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))
for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
if key in flashvars:
max_quality = key
- self._downloader.to_screen(u'[dailymotion] Using %s' % key)
+ self.to_screen(u'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('\\/', '/')
@@ -830,7 +842,7 @@ 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'))
@@ -840,7 +852,7 @@ 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:
@@ -872,17 +884,13 @@ class PhotobucketIE(InfoExtractor):
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
+ self.to_screen(u'%s: Downloading webpage' % video_id)
def _real_extract(self, url):
# 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)
@@ -895,14 +903,14 @@ 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))
@@ -910,7 +918,7 @@ 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')
@@ -941,17 +949,13 @@ class YahooIE(InfoExtractor):
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
+ self.to_screen(u'%s: Downloading webpage' % video_id)
def _real_extract(self, url, new_video=True):
# 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)
@@ -964,18 +968,18 @@ 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)
@@ -988,34 +992,34 @@ 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:
@@ -1024,13 +1028,13 @@ 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)
@@ -1046,13 +1050,13 @@ 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' tag: %s' % url)
+ (1, 'url', u'Could not find tag: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1294,10 +1290,10 @@ class ArteTvIE(InfoExtractor):
'(.*?) ',
re.DOTALL,
[
- (1, 'id', u'ERROR: could not extract video id: %s' % url),
- (2, 'title', u'ERROR: could not extract video title: %s' % url),
- (3, 'date', u'ERROR: could not extract video date: %s' % url),
- (4, 'url', u'ERROR: could not extract video url: %s' % url)
+ (1, 'id', u'could not extract video id: %s' % url),
+ (2, 'title', u'could not extract video title: %s' % url),
+ (3, 'date', u'could not extract video date: %s' % url),
+ (4, 'url', u'could not extract video url: %s' % url)
]
)
@@ -1337,12 +1333,8 @@ class GenericIE(InfoExtractor):
def report_download_webpage(self, video_id):
"""Report webpage download."""
if not self._downloader.params.get('test', False):
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+ self._downloader.report_warning(u'Falling back on generic information extractor.')
+ self.to_screen(u'%s: Downloading webpage' % video_id)
def report_following_redirect(self, new_url):
"""Report information extraction."""
@@ -1412,7 +1404,7 @@ class GenericIE(InfoExtractor):
except ValueError as err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
self.report_extraction(video_id)
@@ -1425,13 +1417,13 @@ class GenericIE(InfoExtractor):
# Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.report_error(u'Invalid URL: %s' % url)
return
video_url = compat_urllib_parse.unquote(mobj.group(1))
@@ -1449,14 +1441,14 @@ class GenericIE(InfoExtractor):
# and so on and so forth; it's just not practical
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)
@@ -1488,35 +1480,31 @@ 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(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
+ self._get_n_results(query, self._max_youtube_results)
else:
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.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
+ return self._get_n_results(query, n)
except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
video_ids = []
pagenum = 0
@@ -1529,12 +1517,12 @@ class YoutubeSearchIE(InfoExtractor):
try:
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')
+ self._downloader.report_error(u'[youtube] No video results')
return
new_ids = list(video['id'] for video in api_response['items'])
@@ -1545,9 +1533,8 @@ class YoutubeSearchIE(InfoExtractor):
if len(video_ids) > n:
video_ids = video_ids[:n]
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
+ return videos
class GoogleSearchIE(InfoExtractor):
@@ -1565,12 +1552,12 @@ class GoogleSearchIE(InfoExtractor):
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+ self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum))
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(':')
@@ -1586,7 +1573,7 @@ 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.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
@@ -1610,7 +1597,7 @@ 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
@@ -1649,12 +1636,12 @@ class YahooSearchIE(InfoExtractor):
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+ self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum))
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(':')
@@ -1670,7 +1657,7 @@ 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.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
@@ -1695,7 +1682,7 @@ 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
@@ -1728,9 +1715,7 @@ class YoutubePlaylistIE(InfoExtractor):
(?:
(?:course|view_play_list|my_playlists|artist|playlist|watch)
\? (?:.*?&)*? (?:p|a|list)=
- | user/.*?/user/
| p/
- | user/.*?#[pg]/c/
)
((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
.*
@@ -1757,7 +1742,7 @@ class YoutubePlaylistIE(InfoExtractor):
# Extract playlist id
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
# Download playlist videos from API
@@ -1772,18 +1757,24 @@ class YoutubePlaylistIE(InfoExtractor):
try:
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
try:
response = json.loads(page)
except ValueError as err:
- self._downloader.trouble(u'ERROR: Invalid JSON in API response: ' + compat_str(err))
+ self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err))
return
- if not 'feed' in response or not 'entry' in response['feed']:
- self._downloader.trouble(u'ERROR: Got a malformed response from YouTube API')
+ if 'feed' not in response:
+ self._downloader.report_error(u'Got a malformed response from YouTube API')
return
+ if 'entry' not in response['feed']:
+ # Number of videos is a multiple of self._MAX_RESULTS
+ break
+
+ playlist_title = response['feed']['title']['$t']
+
videos += [ (entry['yt$position']['$t'], entry['content']['src'])
for entry in response['feed']['entry']
if 'content' in entry ]
@@ -1793,74 +1784,83 @@ class YoutubePlaylistIE(InfoExtractor):
page_num += 1
videos = [v[1] for v in sorted(videos)]
- total = len(videos)
-
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- if playlistend == -1:
- videos = videos[playliststart:]
- else:
- videos = videos[playliststart:playlistend]
-
- if len(videos) == total:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
- else:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(videos)))
- url_results = [self.url_result(url) for url in videos]
- return [self.playlist_result(url_results)]
+ url_results = [self.url_result(url, 'Youtube') for url in videos]
+ return [self.playlist_result(url_results, playlist_id, playlist_title)]
class YoutubeChannelIE(InfoExtractor):
"""Information Extractor for YouTube channels."""
- _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+ _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
+ _MORE_PAGES_INDICATOR = 'yt-uix-load-more'
+ _MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
def report_download_page(self, channel_id, pagenum):
"""Report attempt to download channel page with given number."""
self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+ def extract_videos_from_page(self, page):
+ ids_in_page = []
+ for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ return ids_in_page
+
def _real_extract(self, url):
# 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
+ # Download channel page
channel_id = mobj.group(1)
video_ids = []
pagenum = 1
- while True:
- self.report_download_page(channel_id, pagenum)
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- request = compat_urllib_request.Request(url)
- 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))
- return
+ self.report_download_page(channel_id, pagenum)
+ url = self._TEMPLATE_URL % (channel_id, pagenum)
+ request = compat_urllib_request.Request(url)
+ 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.report_error(u'unable to download webpage: %s' % compat_str(err))
+ return
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ # Extract video identifiers
+ ids_in_page = self.extract_videos_from_page(page)
+ video_ids.extend(ids_in_page)
- if self._MORE_PAGES_INDICATOR not in page:
- break
- pagenum = pagenum + 1
+ # Download any subsequent channel pages using the json-based channel_ajax query
+ if self._MORE_PAGES_INDICATOR in page:
+ while True:
+ pagenum = pagenum + 1
+
+ self.report_download_page(channel_id, pagenum)
+ url = self._MORE_PAGES_URL % (pagenum, channel_id)
+ request = compat_urllib_request.Request(url)
+ 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.report_error(u'unable to download webpage: %s' % compat_str(err))
+ return
+
+ page = json.loads(page)
+
+ ids_in_page = self.extract_videos_from_page(page['content_html'])
+ video_ids.extend(ids_in_page)
+
+ if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
+ break
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
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)]
+ url_entries = [self.url_result(url, 'Youtube') for url in urls]
+ return [self.playlist_result(url_entries, channel_id)]
class YoutubeUserIE(InfoExtractor):
@@ -1885,7 +1885,7 @@ 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)
@@ -1907,7 +1907,7 @@ 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
@@ -1930,21 +1930,9 @@ class YoutubeUserIE(InfoExtractor):
pagenum += 1
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
-
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)]
+ url_results = [self.url_result(url, 'Youtube') for url in urls]
+ return [self.playlist_result(url_results, playlist_title = username)]
class BlipTVUserIE(InfoExtractor):
@@ -1959,14 +1947,14 @@ class BlipTVUserIE(InfoExtractor):
def report_download_page(self, username, pagenum):
"""Report attempt to download user page."""
- self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
- (self.IE_NAME, username, pagenum))
+ self.to_screen(u'user %s: Downloading video ids from page %d' %
+ (username, pagenum))
def _real_extract(self, url):
# 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)
@@ -1980,7 +1968,7 @@ 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
@@ -1999,7 +1987,7 @@ class BlipTVUserIE(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' % str(err))
+ self._downloader.report_error(u'unable to download webpage: %s' % str(err))
return
# Extract video identifiers
@@ -2022,21 +2010,9 @@ class BlipTVUserIE(InfoExtractor):
pagenum += 1
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- 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)))
-
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)]
+ url_entries = [self.url_result(url, 'BlipTV') for url in urls]
+ return [self.playlist_result(url_entries, playlist_title = username)]
class DepositFilesIE(InfoExtractor):
@@ -2046,11 +2022,7 @@ class DepositFilesIE(InfoExtractor):
def report_download_webpage(self, file_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
+ self.to_screen(u'%s: Downloading webpage' % file_id)
def _real_extract(self, url):
file_id = url.split('/')[-1]
@@ -2064,7 +2036,7 @@ 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
@@ -2074,9 +2046,9 @@ 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)
@@ -2085,7 +2057,7 @@ 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')
@@ -2109,7 +2081,7 @@ class FacebookIE(InfoExtractor):
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME)
+ self.to_screen(u'Logging in')
def _real_initialize(self):
if self._downloader is None:
@@ -2158,14 +2130,14 @@ class FacebookIE(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')
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id)
- BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n'
+ BEFORE = '{swf.addParam(param[0], param[1]);});\n'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
if not m:
@@ -2173,12 +2145,14 @@ class FacebookIE(InfoExtractor):
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse.unquote(data['params'])
params = json.loads(params_raw)
- video_url = params['hd_src']
+ video_data = params['video_data'][0]
+ video_url = video_data.get('hd_src')
if not video_url:
- video_url = params['sd_src']
+ video_url = video_data['sd_src']
if not video_url:
raise ExtractorError(u'Cannot find video URL')
- video_duration = int(params['video_duration'])
+ video_duration = int(video_data['video_duration'])
+ thumbnail = video_data['thumbnail_src']
m = re.search('', webpage)
if not m:
@@ -2191,7 +2165,7 @@ class FacebookIE(InfoExtractor):
'url': video_url,
'ext': 'mp4',
'duration': video_duration,
- 'thumbnail': params['thumbnail_src'],
+ 'thumbnail': thumbnail,
}
return [info]
@@ -2203,18 +2177,14 @@ class BlipTVIE(InfoExtractor):
_URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv'
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
-
def report_direct_download(self, title):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
+ self.to_screen(u'%s: Direct download detected' % title)
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)
@@ -2261,7 +2231,7 @@ 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:
@@ -2292,7 +2262,7 @@ 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]
@@ -2307,14 +2277,10 @@ class MyVideoIE(InfoExtractor):
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
-
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)
@@ -2324,16 +2290,16 @@ 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)
@@ -2388,14 +2354,11 @@ class ComedyCentralIE(InfoExtractor):
"""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_extraction(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
-
def report_config_download(self, episode_id, media_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id))
+ self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id))
def report_index_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
+ self.to_screen(u'%s: Downloading show index' % episode_id)
def _print_formats(self, formats):
print('Available formats:')
@@ -2406,7 +2369,7 @@ 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'):
@@ -2437,16 +2400,16 @@ 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')
@@ -2459,7 +2422,7 @@ 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])]
@@ -2470,7 +2433,7 @@ 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 = []
@@ -2491,7 +2454,7 @@ 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)
@@ -2501,7 +2464,7 @@ 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):
@@ -2549,16 +2512,13 @@ class EscapistIE(InfoExtractor):
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P[^/]+)/(?P[^/?]+)[/?]?.*$'
IE_NAME = u'escapist'
- def report_extraction(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
-
def report_config_download(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+ self.to_screen(u'%s: Downloading configuration' % showName)
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')
@@ -2570,7 +2530,7 @@ 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)
@@ -2730,7 +2682,7 @@ 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)
@@ -2765,16 +2717,12 @@ class SoundcloudIE(InfoExtractor):
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))
+ self.to_screen(u'%s: Resolving id' % 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)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
# extract uploader (which is in the url)
@@ -2792,7 +2740,7 @@ 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)
@@ -2805,7 +2753,7 @@ 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)
@@ -2821,28 +2769,101 @@ 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.to_screen(u'%s: Resolving id' % video_id)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.report_error(u'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.report_error(u'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.report_error(u'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.report_error(u'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"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (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)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
webpage = self._download_webpage(url, video_id=url)
self.report_extraction(url)
# Extract video URL
- mobj = re.search(r"jsclassref='([^']*)'", webpage)
+ 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
@@ -2850,7 +2871,7 @@ 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)
@@ -2888,11 +2909,7 @@ class MixcloudIE(InfoExtractor):
def report_download_json(self, file_id):
"""Report JSON download."""
- self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+ self.to_screen(u'Downloading json')
def get_urls(self, jsonData, fmt, bitrate='best'):
"""Get urls from 'audio_formats' section in json"""
@@ -2933,7 +2950,7 @@ 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')
@@ -2947,7 +2964,7 @@ 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
@@ -2971,7 +2988,7 @@ 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)
@@ -2999,11 +3016,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
def report_download_webpage(self, objid):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+ self.to_screen(u'%s: Downloading webpage' % objid)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -3025,14 +3038,14 @@ 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]
@@ -3084,7 +3097,7 @@ 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']
@@ -3109,14 +3122,10 @@ class MTVIE(InfoExtractor):
_VALID_URL = r'^(?Phttps?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P[0-9]+)/[^/]+$'
IE_NAME = u'mtv'
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (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)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
if not mobj.group('proto'):
url = 'http://' + url
@@ -3126,25 +3135,25 @@ 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)
@@ -3154,7 +3163,7 @@ 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)
@@ -3168,7 +3177,7 @@ class MTVIE(InfoExtractor):
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
video_url = rendition.find('./src').text
except KeyError:
- self._downloader.trouble('Invalid rendition field.')
+ self._downloader.report_error('Invalid rendition field.')
return
info = {
@@ -3189,11 +3198,7 @@ class YoukuIE(InfoExtractor):
def report_download_webpage(self, file_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id))
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+ self.to_screen(u'%s: Downloading webpage' % file_id)
def _gen_sid(self):
nowTime = int(time.time() * 1000)
@@ -3226,7 +3231,7 @@ 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')
@@ -3237,7 +3242,7 @@ 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)
@@ -3268,7 +3273,7 @@ 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=[]
@@ -3306,16 +3311,12 @@ class XNXXIE(InfoExtractor):
def report_webpage(self, video_id):
"""Report information extraction"""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction"""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+ self.to_screen(u'%s: Downloading webpage' % 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)
+ self._downloader.report_error(u'invalid URL: %s' % url)
return
video_id = mobj.group(1)
@@ -3326,24 +3327,24 @@ 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)
@@ -3370,29 +3371,29 @@ class GooglePlusIE(InfoExtractor):
def report_extract_entry(self, url):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url)
+ self.to_screen(u'Downloading entry: %s' % url)
def report_date(self, upload_date):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
+ self.to_screen(u'Entry date: %s' % upload_date)
def report_uploader(self, uploader):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader)
+ self.to_screen(u'Uploader: %s' % uploader)
def report_title(self, video_title):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Title: %s' % video_title)
+ self.to_screen(u'Title: %s' % video_title)
def report_extract_vid_page(self, video_page):
"""Report information extraction."""
- self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page)
+ self.to_screen(u'Extracting video page: %s' % video_page)
def _real_extract(self, url):
# 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)
@@ -3406,7 +3407,7 @@ 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
@@ -3441,14 +3442,14 @@ 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)
@@ -3458,7 +3459,7 @@ 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)
@@ -3490,7 +3491,7 @@ 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)
@@ -3530,14 +3531,10 @@ class JustinTVIE(InfoExtractor):
_JUSTIN_PAGE_LIMIT = 100
IE_NAME = u'justin.tv'
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
-
def report_download_page(self, channel, offset):
"""Report attempt to download a single page of videos."""
- self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' %
- (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
+ self.to_screen(u'%s: Downloading video information from %d to %d' %
+ (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
# Return count of items, list of *valid* items
def _parse_page(self, url):
@@ -3546,13 +3543,13 @@ 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:
@@ -3577,7 +3574,7 @@ 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'
@@ -3612,7 +3609,7 @@ 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')
@@ -3620,13 +3617,15 @@ class FunnyOrDieIE(InfoExtractor):
m = re.search(r']*>\s*]*>\s*\s+(?P.*?)", webpage)
+ m = re.search(r"(?P.*?) ", webpage, flags=re.DOTALL)
if not m:
- self._downloader.trouble(u'Cannot find video title')
- title = unescapeHTML(m.group('title'))
+ m = re.search(r'(?P[^<]+?) ', webpage)
+ if not m:
+ self._downloader.report_error(u'Cannot find video title')
+ title = clean_html(m.group('title'))
m = re.search(r' \d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\},"
gameID = m.group('gameID')
- videourl = 'http://store.steampowered.com/video/%s/' % gameID
+ videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
+ self.report_age_confirmation()
webpage = self._download_webpage(videourl, gameID)
+ game_title = re.search(r'', webpage).group('game_title')
+
+ urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\},"
mweb = re.finditer(urlRE, webpage)
namesRE = r'(?P.+?) '
titles = re.finditer(namesRE, webpage)
@@ -3673,7 +3675,7 @@ 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,
@@ -3682,7 +3684,7 @@ class SteamIE(InfoExtractor):
'thumbnail': video_thumb
}
videos.append(info)
- return videos
+ return [self.playlist_result(videos, gameID, game_title)]
class UstreamIE(InfoExtractor):
_VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P\d+)'
@@ -3706,6 +3708,62 @@ class UstreamIE(InfoExtractor):
}
return [info]
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P.*)'
+ 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.report_error(u'Cannot find video url for %s' % video_id)
+ return
+
+ _title = r"""(.*) """
+
+ 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[^/]+)$'
@@ -3763,7 +3821,7 @@ 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')
@@ -3808,7 +3866,7 @@ class YouPornIE(InfoExtractor):
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.to_screen(u'Links found: %d' % len(links))
formats = []
for link in links:
@@ -3844,7 +3902,7 @@ class YouPornIE(InfoExtractor):
return
req_format = self._downloader.params.get('format', None)
- self._downloader.to_screen(u'[youporn] Format: %s' % req_format)
+ self.to_screen(u'Format: %s' % req_format)
if req_format is None or req_format == 'best':
return [formats[0]]
@@ -3855,7 +3913,7 @@ 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]
@@ -3868,7 +3926,7 @@ 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')
@@ -3881,7 +3939,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_URL_RE = r'url: "(?Phttp://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'))
@@ -3889,7 +3947,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_UPLOADED_RE = r'Added (?P
[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')
@@ -3910,7 +3968,7 @@ 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')
@@ -4003,7 +4061,7 @@ class KeekIE(InfoExtractor):
video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
webpage = self._download_webpage(url, video_id)
- m = re.search(r' [\S\s]+?(?P.+?) ', webpage)
uploader = clean_html(m.group('uploader'))
@@ -4039,8 +4097,8 @@ class TEDIE(InfoExtractor):
else :
playlist_id=m.group('playlist_id')
name=m.group('name')
- self._downloader.to_screen(u'[%s] Getting info of playlist %s: "%s"' % (self.IE_NAME,playlist_id,name))
- return self._playlist_videos_info(url,name,playlist_id)
+ self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
+ return [self._playlist_videos_info(url,name,playlist_id)]
def _talk_video_link(self,mediaSlug):
'''Returns the video link for that mediaSlug'''
@@ -4057,12 +4115,17 @@ class TEDIE(InfoExtractor):
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=[]
+
+ playlist_RE = r'div class="headline">(\s*?)(\s*?)(?P.*?) '
+ m_playlist = re.search(playlist_RE, webpage)
+ playlist_title = m_playlist.group('playlist_title')
+
+ playlist_entries = []
for m_video, m_name in zip(m_videos,m_names):
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
+ playlist_entries.append(self.url_result(talk_url, 'TED'))
+ return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url"""
@@ -4070,7 +4133,7 @@ class TEDIE(InfoExtractor):
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'(?P.*) '
+ title_RE=r'(?P.*) '
title=re.search(title_RE, webpage).group('title')
info_RE=r'''