From 382e05fa5686ea58606f684f3032b91801ece8f3 Mon Sep 17 00:00:00 2001 From: t0mm0 Date: Sun, 4 Jan 2015 00:05:31 +0000 Subject: [PATCH 1/3] [tf1] add support for TFOU --- youtube_dl/extractor/tf1.py | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 6e61cc9e2..384b4c3f8 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.*?)\.html' - _TEST = { + _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P\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 +21,25 @@ 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': '7085291', + 'ext': 'mp4', + 'title': 'Le grand Mystérioso - Chuggington', + 'description': 'Emery rêve qu\'un article lui soit consacré dans le journal.', + }, + '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'["\'](http(?:s)?://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') From 2bf098eda43f0c789e04f7f633149cc99873d182 Mon Sep 17 00:00:00 2001 From: t0mm0 Date: Sun, 4 Jan 2015 00:43:55 +0000 Subject: [PATCH 2/3] [tf1] fix test --- youtube_dl/extractor/tf1.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 384b4c3f8..5c0fcef58 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -24,10 +24,11 @@ class TF1IE(InfoExtractor): }, { 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', 'info_dict': { - 'id': '7085291', + 'id': '12043945', 'ext': 'mp4', 'title': 'Le grand Mystérioso - Chuggington', - 'description': 'Emery rêve qu\'un article lui soit consacré dans le journal.', + '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 From b158bb86934fb8863a697b6e65a1cbc5105d1741 Mon Sep 17 00:00:00 2001 From: t0mm0 Date: Sun, 4 Jan 2015 00:45:23 +0000 Subject: [PATCH 3/3] [tf1] simplify regex --- youtube_dl/extractor/tf1.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 5c0fcef58..07cc81226 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -40,7 +40,7 @@ class TF1IE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) embed_url = self._html_search_regex( - r'["\'](http(?:s)?://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')