Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[tf1] Improve extraction and fix issues (closes #21372)

Browse Source
This commit is contained in:
Sergey M․ 2019-06-22 00:37:49 +07:00
parent 9c2aaac268
commit 1c11204056
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 25 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
youtube_dl/extractor/tf1.py
View File

@ -2,8 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import js_to_json
class TF1IE(InfoExtractor): class TF1IE(InfoExtractor):
@ -62,23 +61,32 @@ class TF1IE(InfoExtractor):
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 wat_id = None
if vids_data_string is not None:
vids_data = self._parse_json( data = self._parse_json(
vids_data_string, video_id, self._search_regex(
transform_source=js_to_json) r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
video_data = [v for v in vids_data.values() 'data', default='{}'), video_id, fatal=False)
if 'slug' in v and v['slug'] == video_id]
if len(video_data) > 0 and 'streamId' in video_data[0]: if data:
wat_id = video_data[0]['streamId'] try:
if wat_id is None: wat_id = next(
video.get('streamId')
for key, video in data.items()
if isinstance(video, dict)
and video.get('slug') == video_id)
if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
wat_id = None
except StopIteration:
pass
if not wat_id:
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' 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')