w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[tf1] Fix wat id extraction (closes #21365)

Browse source
This commit is contained in:
Emmanuel Froissart 2019-06-12 13:55:07 +02:00 committed by Sergey M․
parent d415957dbc
commit 9c2aaac268
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 33 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/tf1.py
View file

@ -3,6 +3,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import js_to_json
class TF1IE(InfoExtractor): class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player.""" """TF1 uses the wat.tv player."""
@ -43,12 +45,40 @@ class TF1IE(InfoExtractor):
}, { }, {
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html', 'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
'info_dict': {
'id': '13641379',
'ext': 'mp4',
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
'upload_date': '20190611',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
vids_data_string = self._html_search_regex(
r'<script>\s*window\.__APOLLO_STATE__\s*=\s*(?P<vids_data_string>\{.*?\})\s*;?\s*</script>',
webpage, 'videos data string', group='vids_data_string', default=None)
wat_id = None
if vids_data_string is not None:
vids_data = self._parse_json(
vids_data_string, video_id,
transform_source=js_to_json)
video_data = [v for v in vids_data.values()
if 'slug' in v and v['slug'] == video_id]
if len(video_data) > 0 and 'streamId' in video_data[0]:
wat_id = video_data[0]['streamId']
if wat_id is None:
wat_id = self._html_search_regex( wat_id = self._html_search_regex(
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1', [r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'
],
webpage, 'wat id', group='id') webpage, 'wat id', group='id')
return self.url_result('wat:%s' % wat_id, 'Wat') return self.url_result('wat:%s' % wat_id, 'Wat')