diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/kankan.py | 37 | ||||
-rw-r--r-- | youtube_dl/extractor/tf1.py | 8 | ||||
-rw-r--r-- | youtube_dl/extractor/vevo.py | 4 | ||||
-rw-r--r-- | youtube_dl/extractor/wat.py | 18 |
5 files changed, 45 insertions, 23 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9f4dd3c24..c20172a53 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -38,6 +38,7 @@ from .infoq import InfoQIE from .instagram import InstagramIE from .jukebox import JukeboxIE from .justintv import JustinTVIE +from .kankan import KankanIE from .keek import KeekIE from .liveleak import LiveLeakIE from .livestream import LivestreamIE diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py new file mode 100644 index 000000000..8537ba584 --- /dev/null +++ b/youtube_dl/extractor/kankan.py @@ -0,0 +1,37 @@ +import re + +from .common import InfoExtractor +from ..utils import determine_ext + + +class KankanIE(InfoExtractor): + _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml' + + _TEST = { + u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml', + u'file': u'48863.flv', + u'md5': u'29aca1e47ae68fc28804aca89f29507e', + u'info_dict': { + u'title': u'Ready To Go', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + title = self._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title') + gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid') + + video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid, + video_id, u'Downloading video url info') + ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip') + path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path') + video_url = 'http://%s%s' % (ip, path) + + return {'id': video_id, + 'title': title, + 'url': video_url, + 'ext': determine_ext(video_url), + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index a8af89f83..7d1071cbf 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -6,16 +6,12 @@ import re from .common import InfoExtractor class TF1IE(InfoExtractor): - """ - TF1 uses the wat.tv player, currently it can only download videos with the - html5 player enabled, it cannot download HD videos. - """ - _WORKING = False + """TF1 uses the wat.tv player.""" _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html' _TEST = { u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', u'file': u'10635995.mp4', - u'md5': u'66789d3e91278d332f75e1feb7aea327', + u'md5': u'2e378cc28b9957607d5e88f274e637d8', u'info_dict': { u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle', u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 3b16dcfbc..67537eae5 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -35,12 +35,12 @@ class VevoIE(InfoExtractor): self.report_extraction(video_id) video_info = json.loads(info_json) - m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):(?P<url>.*?)"', links_webpage)) + m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):/?(?P<url>.*?)"', links_webpage)) if m_urls is None or len(m_urls) == 0: raise ExtractorError(u'Unable to extract video url') # They are sorted from worst to best quality m_url = m_urls[-1] - video_url = base_url + m_url.group('url') + video_url = base_url + '/' + m_url.group('url') ext = m_url.group('ext') return {'url': video_url, diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 0407a2d26..6ac391225 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -12,13 +12,13 @@ from ..utils import ( class WatIE(InfoExtractor): - _WORKING = False _VALID_URL=r'http://www.wat.tv/.*-(?P<shortID>.*?)_.*?.html' IE_NAME = 'wat.tv' _TEST = { u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', u'file': u'10631273.mp4', - u'md5': u'0a4fe7870f31eaeabb5e25fd8da8414a', + # Sometimes wat serves the whole file with the --test option + u'md5': u'd8b2231e1e333acd12aad94b80937e19', u'info_dict': { u'title': u'World War Z - Philadelphia VOST', u'description': u'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', @@ -59,20 +59,8 @@ class WatIE(InfoExtractor): # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url - player_data = compat_urllib_parse.urlencode({'shortVideoId': short_id, - 'html5': '1'}) - player_info = self._download_webpage('http://www.wat.tv/player?' + player_data, - real_id, u'Downloading player info') - player = json.loads(player_info)['player'] - html5_player = self._html_search_regex(r'iframe src="(.*?)"', player, - 'html5 player') - player_webpage = self._download_webpage(html5_player, real_id, - u'Downloading player webpage') - - video_url = self._search_regex(r'urlhtml5 : "(.*?)"', player_webpage, - 'video url') info = {'id': real_id, - 'url': video_url, + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, 'ext': 'mp4', 'title': first_chapter['title'], 'thumbnail': first_chapter['preview'], |