X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=8d428b25dcd1ff828044881b1ff7dd89705fd12d;hb=fcbc8c830e078bd43f90bdc08721229a452b4824;hp=7221ae41e4796adc0830b4ae789556ec3d1e7d26;hpb=392105265ccb3e155fe92b3c0ac15b2b4ff906d3;p=youtube-dl
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 7221ae41e..8d428b25d 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -97,7 +97,25 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r"""^
+ (
+ (?:https?://)? # http(s):// (optional)
+ (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+ tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
+ (?!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
+ (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+ (?:\?|\#!?) # the params delimiter ? or # or #!
+ (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
+ v=
+ )
+ )? # optional -> youtube.com/xxxx is OK
+ )? # all until now is optional -> you can pass the naked ID
+ ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
+ (?(1).+)? # if we found the ID, everything can follow
+ $"""
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -136,6 +154,10 @@ class YoutubeIE(InfoExtractor):
}
IE_NAME = u'youtube'
+ def suitable(self, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language')
@@ -270,7 +292,7 @@ class YoutubeIE(InfoExtractor):
url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
# Extract video id from URL
- 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)
return
@@ -404,7 +426,7 @@ class YoutubeIE(InfoExtractor):
url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
url_data = [parse_qs(uds) for uds in url_data_strs]
url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
- url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+ url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
@@ -594,7 +616,7 @@ class MetacafeIE(InfoExtractor):
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
@@ -615,9 +637,9 @@ class DailymotionIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group(1)
+ video_id = mobj.group(1).split('_')[0].split('?')[0]
- video_extension = 'flv'
+ video_extension = 'mp4'
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
@@ -631,20 +653,23 @@ class DailymotionIE(InfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
+ mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- sequence = urllib.unquote(mobj.group(1))
- mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ flashvars = urllib.unquote(mobj.group(1))
+ if 'hqURL' in flashvars: max_quality = 'hqURL'
+ elif 'sdURL' in flashvars: max_quality = 'sdURL'
+ else: max_quality = 'ldURL'
+ mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
+ if mobj is None:
+ mobj = re.search(r'"video_url":"(.*?)",', flashvars)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
-
- # if needed add http://www.dailymotion.com/ if relative URL
+ video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
- video_url = mediaURL
+ # TODO: support choosing qualities
mobj = re.search(r'', webpage)
if mobj is None:
@@ -1473,7 +1498,7 @@ class YoutubePlaylistIE(InfoExtractor):
_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)?([0-9A-Za-z-_]+)(?:/.*?/([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=(PL)?%s&'
+ _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=.*?%s'
_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
IE_NAME = u'youtube:playlist'
@@ -2959,7 +2984,6 @@ class MTVIE(InfoExtractor):
return [info]
-
class YoukuIE(InfoExtractor):
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[A-Za-z0-9]+)\.html'
@@ -2995,22 +3019,15 @@ class YoukuIE(InfoExtractor):
#return ''.join(mixed)
return mixed
-
def _get_file_id(self, fileId, seed):
mixed = self._get_file_ID_mix_string(seed)
ids = fileId.split('*')
realId = []
for ch in ids:
- if ch is not '':
+ if ch:
realId.append(mixed[int(ch)])
return ''.join(realId)
- def _gen_key(self, key1, key2):
- pass
-
-
-
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -3019,10 +3036,6 @@ class YoukuIE(InfoExtractor):
video_id = mobj.group('ID')
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
-<<<<<<< HEAD
- print info_url
-=======
->>>>>>> 51661d86005ffbdd4debd051cd9683cf5f5c2fe9
request = urllib2.Request(info_url, None, std_headers)
try:
@@ -3079,7 +3092,7 @@ class YoukuIE(InfoExtractor):
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
- print download_url
+
info = {
'id': '%s_part%02d' % (video_id, index),
'url': download_url,
@@ -3091,3 +3104,68 @@ class YoukuIE(InfoExtractor):
files_info.append(info)
return files_info
+
+
+class XNXXIE(InfoExtractor):
+ """Information extractor for xnxx.com"""
+
+ _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+ IE_NAME = u'xnxx'
+ VIDEO_URL_RE = r'flv_url=(.*?)&'
+ VIDEO_TITLE_RE = r'(.*?)\s+-\s+XNXX.COM'
+ VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
+
+ 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))
+
+ 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(1).decode('utf-8')
+
+ self.report_webpage(video_id)
+
+ # Get webpage content
+ try:
+ webpage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: 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')
+ return
+ video_url = urllib.unquote(result.group(1).decode('utf-8'))
+
+ result = re.search(self.VIDEO_TITLE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = result.group(1).decode('utf-8')
+
+ result = re.search(self.VIDEO_THUMB_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = result.group(1).decode('utf-8')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ 'player_url': None}
+
+ return [info]