pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-02-05 02:00:12 +09:00
Code Issues Projects Releases Wiki Activity

Step 1 of a rewrite to find and parse embedded JSON instead of just

Browse Source 
running a regexp over the whole page.  This version passes the tests,
but more work is needed.
This commit is contained in:
Tim Mann 2021-02-13 16:26:33 -08:00
parent ad49e65d1e
commit fd61f317bf
1 changed files with 11 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
youtube_dl/extractor/pac12.py
View File

@ -1,5 +1,7 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from __future__ import print_function #XXX
import pprint #XXX
import re import re
@ -32,9 +34,15 @@ class Pac12IE(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)
video_url = \
self._search_regex(r'"manifest_url":"(?P<url>https:[^"]+)"', drupal_settings = self._parse_json(
webpage, 'url', group='url', default=None) self._search_regex(
r'<script[^>]+type="application/json"[^>]*data-drupal-selector="drupal-settings-json">([^<]+)</script>',
webpage, 'drupal settings'), video_id)
pprint.pprint(drupal_settings.get('currentVideo'))
video_url = drupal_settings.get('currentVideo', {}).get('manifest_url')
vod_url = None vod_url = None
if (video_url is None) or ('vod-' not in url): if (video_url is None) or ('vod-' not in url):
vod_url = self._search_regex(r'(https?://(?:embed\.)?pac-12\.com/(?:embed/)?vod-[0-9a-zA-Z]+)', vod_url = self._search_regex(r'(https?://(?:embed\.)?pac-12\.com/(?:embed/)?vod-[0-9a-zA-Z]+)',