1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 20:55:34 +08:00

Correct some extractor _VALID_URL regexes

This commit is contained in:
dst 2013-12-04 20:34:47 +07:00
parent 8796857429
commit c0ade33e16
40 changed files with 43 additions and 43 deletions

View File

@ -13,7 +13,7 @@ from ..utils import (
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'AddAnime'
_TEST = {
u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',

View File

@ -10,7 +10,7 @@ from ..utils import (
class AppleTrailersIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = {
u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
u"playlist": [

View File

@ -11,7 +11,7 @@ from ..utils import (
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = {
u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',

View File

@ -17,8 +17,8 @@ from ..utils import (
# add tests.
class ArteTvIE(InfoExtractor):
_VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
_LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
_VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
_LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
_LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = u'arte.tv'

View File

@ -16,7 +16,7 @@ class AUEngineIE(InfoExtractor):
u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
}
}
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

View File

@ -54,7 +54,7 @@ class BambuserIE(InfoExtractor):
class BambuserChannelIE(InfoExtractor):
IE_NAME = u'bambuser:channel'
_VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
_VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
# The maximum number we can get with each request
_STEP = 50

View File

@ -4,7 +4,7 @@ from .common import InfoExtractor
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html'
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
_TEST = {
u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',

View File

@ -12,7 +12,7 @@ from ..utils import (
class ComedyCentralIE(MTVIE):
_VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
_VALID_URL = r'https?://(?:www\.)?comedycentral\.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
_FEED_URL = u'http://comedycentral.com/feeds/mrss/'
_TEST = {

View File

@ -6,7 +6,7 @@ from ..utils import (
)
class CSpanIE(InfoExtractor):
_VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
_VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
_TEST = {
u'url': u'http://www.c-spanvideo.org/program/HolderonV',
u'file': u'315139.flv',

View File

@ -11,7 +11,7 @@ from ..utils import (
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
_VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
u'file': u'36983.webm',

View File

@ -10,7 +10,7 @@ from ..utils import (
class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
_VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
_VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
_TEST = {
u"name": u"EightTracks",
u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",

View File

@ -8,7 +8,7 @@ class ExfmIE(InfoExtractor):
IE_NAME = u'exfm'
IE_DESC = u'ex.fm'
_VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
_SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
_SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
_TESTS = [
{
u'url': u'http://ex.fm/song/eh359',

View File

@ -9,7 +9,7 @@ from ..utils import (
class FazIE(InfoExtractor):
IE_NAME = u'faz.net'
_VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html'
_VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
_TEST = {
u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',

View File

@ -12,7 +12,7 @@ from ..utils import (
class FKTVIE(InfoExtractor):
IE_NAME = u'fernsehkritik.tv'
_VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
_VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
_TEST = {
u'url': u'http://fernsehkritik.tv/folge-1',
@ -52,7 +52,7 @@ class FKTVIE(InfoExtractor):
class FKTVPosteckeIE(InfoExtractor):
IE_NAME = u'fernsehkritik.tv:postecke'
_VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
_VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
_TEST = {
u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
u'file': u'0120.flv',

View File

@ -45,7 +45,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = u'francetvinfo.fr'
_VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
_VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
_TEST = {
u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',

View File

@ -4,7 +4,7 @@ from .common import InfoExtractor
class GamekingsIE(InfoExtractor):
_VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
_VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
_TEST = {
u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
u'file': u'20130811.mp4',

View File

@ -7,7 +7,7 @@ class GametrailersIE(MTVIE):
Gametrailers use the same videos system as MTVIE, it just changes the feed
url, where the uri is and the method to get the thumbnails.
"""
_VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
_VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
_TEST = {
u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',

View File

@ -103,7 +103,7 @@ class IGNIE(InfoExtractor):
class OneUPIE(IGNIE):
"""Extractor for 1up.com, it uses the ign videos system."""
_VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
_VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
IE_NAME = '1up.com'
_DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'

View File

@ -3,7 +3,7 @@ import re
from .common import InfoExtractor
class InstagramIE(InfoExtractor):
_VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
_VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
_TEST = {
u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
u'file': u'aye83DjauH.mp4',

View File

@ -8,7 +8,7 @@ from ..utils import (
)
class JukeboxIE(InfoExtractor):
_VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
_VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
_IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
_VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
_TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'

View File

@ -8,7 +8,7 @@ from ..utils import (
class LiveLeakIE(InfoExtractor):
_VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
_VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'liveleak'
_TEST = {
u'url': u'http://www.liveleak.com/view?i=757_1364311680',

View File

@ -11,7 +11,7 @@ from ..utils import (
class LivestreamIE(InfoExtractor):
IE_NAME = u'livestream'
_VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
u'file': u'4719370.mp4',

View File

@ -9,7 +9,7 @@ from ..utils import (
class MuzuTVIE(InfoExtractor):
_VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)'
_VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)'
IE_NAME = u'muzu.tv'
_TEST = {

View File

@ -9,7 +9,7 @@ from ..utils import (
class MySpassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
_VALID_URL = r'http://www\.myspass\.de/.*'
_TEST = {
u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
u'file': u'11741.mp4',

View File

@ -12,7 +12,7 @@ from ..utils import (
)
class ORFIE(InfoExtractor):
_VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
_VALID_URL = r'https?://tvthek\.orf\.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

View File

@ -5,7 +5,7 @@ from .common import InfoExtractor
class PBSIE(InfoExtractor):
_VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
_VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?'
_TEST = {
u'url': u'http://video.pbs.org/video/2365006249/',

View File

@ -11,7 +11,7 @@ from ..utils import (
class RutubeIE(InfoExtractor):
_VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)'
_VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
_TEST = {
u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',

View File

@ -4,7 +4,7 @@ from .common import InfoExtractor
class SlashdotIE(InfoExtractor):
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
_VALID_URL = r'https?://tv\.slashdot\.org/video/\?embed=(?P<id>.*?)(&|$)'
_TEST = {
u'add_ie': ['Ooyala'],

View File

@ -25,7 +25,7 @@ class SoundcloudIE(InfoExtractor):
_VALID_URL = r'''^(?:https?://)?
(?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
|(?P<widget>w.soundcloud.com/player/?.*?url=.*)
|(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
@ -217,7 +217,7 @@ class SoundcloudSetIE(SoundcloudIE):
class SoundcloudUserIE(SoundcloudIE):
_VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
_VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
IE_NAME = u'soundcloud:user'
# it's in tests/test_playlists.py

View File

@ -6,7 +6,7 @@ from ..utils import RegexNotFoundError, ExtractorError
class SpaceIE(InfoExtractor):
_VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video.html'
_VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
_TEST = {
u'add_ie': ['Brightcove'],
u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',

View File

@ -18,7 +18,7 @@ from ..utils import (
class StanfordOpenClassroomIE(InfoExtractor):
IE_NAME = u'stanfordoc'
IE_DESC = u'Stanford Open ClassRoom'
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
_VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
_TEST = {
u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
u'file': u'PracticalUnix_intro-environment.mp4',

View File

@ -7,7 +7,7 @@ from .common import InfoExtractor
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
_VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
_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',

View File

@ -3,7 +3,7 @@ import re
from .common import InfoExtractor
class UnistraIE(InfoExtractor):
_VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
_VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)'
_TEST = {
u'url': u'http://utv.unistra.fr/video.php?id_video=154',

View File

@ -9,7 +9,7 @@ from ..utils import (
)
class VeeHDIE(InfoExtractor):
_VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)'
_VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
_TEST = {
u'url': u'http://veehd.com/video/4686958',

View File

@ -15,7 +15,7 @@ class VevoIE(InfoExtractor):
Accepts urls from vevo.com or in the format 'vevo:{id}'
(currently used by MTVIE)
"""
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
_VALID_URL = r'((http://www\.vevo\.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
_TESTS = [{
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
u'file': u'GB1101300280.mp4',

View File

@ -6,7 +6,7 @@ from ..utils import ExtractorError
class ViceIE(InfoExtractor):
_VALID_URL = r'http://www.vice.com/.*?/(?P<name>.+)'
_VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
_TEST = {
u'url': u'http://www.vice.com/Fringes/cowboy-capitalists-part-1',

View File

@ -8,7 +8,7 @@ from ..utils import (
class ViddlerIE(InfoExtractor):
_VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler\.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://www.viddler.com/v/43903784",
u'file': u'43903784.mp4',

View File

@ -7,7 +7,7 @@ from ..utils import (
)
class VideofyMeIE(InfoExtractor):
_VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)'
_VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
IE_NAME = u'videofy.me'
_TEST = {

View File

@ -11,7 +11,7 @@ from ..utils import (
class WatIE(InfoExtractor):
_VALID_URL=r'http://www.wat.tv/.*-(?P<shortID>.*?)_.*?.html'
_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',

View File

@ -7,7 +7,7 @@ from ..utils import (
class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_TEST = {
u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
u'file': u'2189178.flv',