X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/63a6927374492ef47c8fd6de67d0760ace4dd0ed..11021a3e7a38072a0072edc613930e0a1193196c:/youtube_dl/extractor/francetv.py
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index ad85bc1..51eb97b 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -1,4 +1,7 @@
# encoding: utf-8
+
+from __future__ import unicode_literals
+
import re
import json
@@ -30,7 +33,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
class PluzzIE(FranceTVBaseInfoExtractor):
- IE_NAME = u'pluzz.francetv.fr'
+ IE_NAME = 'pluzz.francetv.fr'
_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
# Can't use tests, videos expire in 7 days
@@ -44,17 +47,17 @@ class PluzzIE(FranceTVBaseInfoExtractor):
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
- IE_NAME = u'francetvinfo.fr'
+ IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P
.+)\.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',
- u'file': u'84981923.mp4',
- u'info_dict': {
- u'title': u'Soir 3',
+ 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+ 'file': '84981923.mp4',
+ 'info_dict': {
+ 'title': 'Soir 3',
},
- u'params': {
- u'skip_download': True,
+ 'params': {
+ 'skip_download': True,
},
}
@@ -62,13 +65,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
- video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+ video_id = self._search_regex(r'id-video=(\d+?)[@"]', webpage, 'video id')
return self._extract_video(video_id)
class FranceTVIE(FranceTVBaseInfoExtractor):
- IE_NAME = u'francetv'
- IE_DESC = u'France 2, 3, 4, 5 and Ã'
+ IE_NAME = 'francetv'
+ IE_DESC = 'France 2, 3, 4, 5 and Ã'
_VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
(?:
emissions/.*?/(videos|emissions)/(?P[^/?]+)
@@ -78,73 +81,73 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
_TESTS = [
# france2
{
- u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
- u'file': u'75540104.mp4',
- u'info_dict': {
- u'title': u'13h15, le samedi...',
- u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+ 'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+ 'file': '75540104.mp4',
+ 'info_dict': {
+ 'title': '13h15, le samedi...',
+ 'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d',
},
- u'params': {
+ 'params': {
# m3u8 download
- u'skip_download': True,
+ 'skip_download': True,
},
},
# france3
{
- u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
- u'info_dict': {
- u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
- u'ext': u'flv',
- u'title': u'Le scandale du prix des médicaments',
- u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+ 'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+ 'info_dict': {
+ 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+ 'ext': 'flv',
+ 'title': 'Le scandale du prix des médicaments',
+ 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
},
- u'params': {
+ 'params': {
# rtmp download
- u'skip_download': True,
+ 'skip_download': True,
},
},
# france4
{
- u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
- u'info_dict': {
- u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
- u'ext': u'flv',
- u'title': u'Hero Corp Making of - Extrait 1',
- u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+ 'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ 'info_dict': {
+ 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ 'ext': 'flv',
+ 'title': 'Hero Corp Making of - Extrait 1',
+ 'description': 'md5:c87d54871b1790679aec1197e73d650a',
},
- u'params': {
+ 'params': {
# rtmp download
- u'skip_download': True,
+ 'skip_download': True,
},
},
# france5
{
- u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
- u'info_dict': {
- u'id': u'92837968',
- u'ext': u'mp4',
- u'title': u'C Ã dire ?!',
- u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+ 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+ 'info_dict': {
+ 'id': '92837968',
+ 'ext': 'mp4',
+ 'title': 'C Ã dire ?!',
+ 'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
},
- u'params': {
+ 'params': {
# m3u8 download
- u'skip_download': True,
+ 'skip_download': True,
},
},
# franceo
{
- u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
- u'info_dict': {
- u'id': u'92327925',
- u'ext': u'mp4',
- u'title': u'Infô-Afrique',
- u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+ 'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+ 'info_dict': {
+ 'id': '92327925',
+ 'ext': 'mp4',
+ 'title': 'Infô-Afrique',
+ 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
},
- u'params': {
+ 'params': {
# m3u8 download
- u'skip_download': True,
+ 'skip_download': True,
},
- u'skip': u'The id changes frequently',
+ 'skip': 'The id changes frequently',
},
]
@@ -160,27 +163,28 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
'\.fr/\?id-video=([^"/&]+)'),
(r'.*)(\?|$)'
_TEST = {
- u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
- u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
- u'info_dict': {
- u'title': u'Génération Quoi - Garde à Vous',
- u'uploader': u'Génération Quoi',
+ 'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+ 'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
+ 'info_dict': {
+ 'title': 'Génération Quoi - Garde à Vous',
+ 'uploader': 'Génération Quoi',
},
- u'params': {
+ 'params': {
# It uses Dailymotion
- u'skip_download': True,
+ 'skip_download': True,
},
+ 'skip': 'Only available from France',
}
def _real_extract(self, url):
@@ -191,3 +195,29 @@ class GenerationQuoiIE(InfoExtractor):
info = json.loads(info_json)
return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
ie='Dailymotion')
+
+
+class CultureboxIE(FranceTVBaseInfoExtractor):
+ IE_NAME = 'culturebox.francetvinfo.fr'
+ _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P.*?)(\?|$)'
+
+ _TEST = {
+ 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+ 'info_dict': {
+ 'id': 'EV_6785',
+ 'ext': 'mp4',
+ 'title': 'Einstein on the beach au Théâtre du Châtelet',
+ 'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ webpage = self._download_webpage(url, name)
+ video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id')
+ return self._extract_video(video_id)