aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2015-01-04 02:08:38 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2015-01-04 02:08:38 +0100
commit788fa208c86d7196c75bdc74d8106a489723c054 (patch)
treecc9ab8681576cdd10a48d64129e9459aedfc9ba3 /youtube_dl/extractor
parent8848314c08284f6a4b8f3c3529bf2e3f1b72610c (diff)
parent3e3327ea175b88f668a2b8cd220042b0950c00d4 (diff)
Merge branch 'master' of github.com:rg3/youtube-dl
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/tf1.py22
1 files changed, 17 insertions, 5 deletions
diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py
index 6e61cc9e2..07cc81226 100644
--- a/youtube_dl/extractor/tf1.py
+++ b/youtube_dl/extractor/tf1.py
@@ -8,8 +8,8 @@ from .common import InfoExtractor
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
- _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html'
- _TEST = {
+ _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
+ _TESTS = {
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': {
'id': '10635995',
@@ -21,14 +21,26 @@ class TF1IE(InfoExtractor):
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
+ }, {
+ 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
+ 'info_dict': {
+ 'id': '12043945',
+ 'ext': 'mp4',
+ 'title': 'Le grand Mystérioso - Chuggington',
+ 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
+ 'upload_date': '20150103',
+ },
+ 'params': {
+ # Sometimes wat serves the whole file with the --test option
+ 'skip_download': True,
+ },
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
embed_url = self._html_search_regex(
- r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url')
+ r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed player page')
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')