Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[tf1] fix wat id extraction (closes ytdl-org#21365) #21372

Closed
wants to merge 9 commits into from
Closed

[tf1] fix wat id extraction (closes ytdl-org#21365) #21372

Changes from 2 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
8f738c2
[tf1] fix wat id extraction(closes ytdl-org#21365)
Jun 12, 2019
6e6151a
[tf1] relax wat id regex
Jun 12, 2019
77d6e33
[tf1] reintroduce old wat id pattern
Jun 12, 2019
ae4df7d
[tf1] proper multipattern and relaxed regex
Jun 12, 2019
eb5d7a4
remove unused import
Jun 12, 2019
c0319bc
replaced long strings with md5
Jun 12, 2019
acda141
disambiguated id patterns using the slug
Jun 12, 2019
c381d37
extract wat_id by parsing JSON
Jun 14, 2019
c352f74
improved regex to extract videos data
Jun 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions youtube_dl/extractor/tf1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,9 @@

from .common import InfoExtractor

from youtube_dl.utils import (
RegexNotFoundError,
froiss marked this conversation as resolved.
Show resolved Hide resolved
)

class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
Expand Down Expand Up @@ -61,7 +64,13 @@ class TF1IE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
wat_id = self._html_search_regex(
r'"streamId":"(?P<id>\d{8})"',
webpage, 'wat id', group='id')
try:
wat_id = self._html_search_regex(
# the old pattern. Should no longer work as of 2019-06-12
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
webpage, 'wat id', group='id')
except RegexNotFoundError:
wat_id = self._html_search_regex(
r'\bstreamId\W+(?P<id>\d+)',
froiss marked this conversation as resolved.
Show resolved Hide resolved
webpage, 'wat id', group='id')
froiss marked this conversation as resolved.
Show resolved Hide resolved
return self.url_result('wat:%s' % wat_id, 'Wat')