aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-12-05 22:30:04 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2013-12-05 22:30:04 +0100
commit72135030d1235f608a2b5e0ec007ca8e6e19e3b4 (patch)
tree4520c4c0bef2e0daa862d08cb1c6896f258cf0e4 /youtube_dl
parent19e3dfc9f8444a1341a6e71752a3235a0447a565 (diff)
parent3514813d5b021c5595b212ba3b1801175840c5c0 (diff)
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/francetv.py104
2 files changed, 86 insertions, 20 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 2e1a8be14..a78dcad7f 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -56,7 +56,7 @@ from .flickr import FlickrIE
from .francetv import (
PluzzIE,
FranceTvInfoIE,
- France2IE,
+ FranceTVIE,
GenerationQuoiIE
)
from .freesound import FreesoundIE
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index 66aa3aa0d..ad85bc16d 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -21,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
thumbnail_path = info.find('image').text
return {'id': video_id,
- 'ext': 'mp4',
+ 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
'url': video_url,
'title': info.find('titre').text,
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
@@ -66,35 +66,101 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
return self._extract_video(video_id)
-class France2IE(FranceTVBaseInfoExtractor):
- IE_NAME = u'france2.fr'
- _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+class FranceTVIE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'francetv'
+ IE_DESC = u'France 2, 3, 4, 5 and Ô'
+ _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
(?:
- emissions/.*?/videos/(?P<id>\d+)
- | emission/(?P<key>[^/?]+)
+ emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
+ | (emissions?|jt)/(?P<key>[^/?]+)
)'''
- _TEST = {
- 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',
+ _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',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
},
- u'params': {
- u'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',
+ },
+ u'params': {
+ # rtmp download
+ u'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',
+ },
+ u'params': {
+ # rtmp download
+ u'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 à dire ?!',
+ u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+ },
+ u'params': {
+ # m3u8 download
+ u'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',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
+ u'skip': u'The id changes frequently',
+ },
+ ]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('key'):
webpage = self._download_webpage(url, mobj.group('key'))
- video_id = self._html_search_regex(
- r'''(?x)<div\s+class="video-player">\s*
+ id_res = [
+ (r'''(?x)<div\s+class="video-player">\s*
<a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
- class="francetv-video-player">''',
- webpage, u'video ID')
+ class="francetv-video-player">'''),
+ (r'<a id="player_direct" href="http://info\.francetelevisions'
+ '\.fr/\?id-video=([^"/&]+)'),
+ (r'<a class="video" id="ftv_player_(.+?)"'),
+ ]
+ video_id = self._html_search_regex(id_res, webpage, u'video ID')
else:
video_id = mobj.group('id')
return self._extract_video(video_id)