Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 15:25:49 +00:00
Code Issues Projects Releases Wiki Activity

[pbs] Add support for flp frontlines (Closes #7369)

Browse Source
This commit is contained in:
Sergey M․ 2015-11-07 00:39:16 +06:00
parent 0fa6b17dcc
commit 686f98816e
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/pbs.py
View File

@ -8,6 +8,7 @@
ExtractorError,
determine_ext,
int_or_none,
strip_jsonp,
unified_strdate,
US_RATINGS,
)
@ -191,6 +192,23 @@ def _extract_webpage(self, url):
if media_id:
return media_id, presumptive_id, upload_date
# Fronline video embedded via flp
video_id = self._search_regex(
r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')
if video_id:
# pkg_id calculation is reverse engineered from
# http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
prg_id = self._search_regex(
r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
if 'q' in prg_id:
prg_id = prg_id.split('q')[1]
prg_id = int(prg_id, 16)
getdir = self._download_json(
'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
presumptive_id, 'Downloading getdir JSON',
transform_source=strip_jsonp)
return getdir['mid'], presumptive_id, upload_date
for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
url = self._search_regex(
r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,