midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[cspan] Extract info from jwplayer data (closes #3672, closes #3734, closes #10638, closes #13030, closes #18806, closes #23148, closes #24461, closes #26171, closes #26800, closes #27263)

Browse source
This commit is contained in:
Sergey M․ 2020-12-01 01:53:12 +07:00
parent be19ae11fd
commit 3e4e338133
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 23 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/cspan.py
View file

@ -10,6 +10,8 @@ from ..utils import (
find_xpath_attr, find_xpath_attr,
get_element_by_class, get_element_by_class,
int_or_none, int_or_none,
js_to_json,
merge_dicts,
smuggle_url, smuggle_url,
unescapeHTML, unescapeHTML,
) )
@ -98,6 +100,26 @@ class CSpanIE(InfoExtractor):
bc_attr['data-bcid']) bc_attr['data-bcid'])
return self.url_result(smuggle_url(bc_url, {'source_url': url})) return self.url_result(smuggle_url(bc_url, {'source_url': url}))
def add_referer(formats):
for f in formats:
f.setdefault('http_headers', {})['Referer'] = url
# As of 01.12.2020 this path looks to cover all cases making the rest
# of the code unnecessary
jwsetup = self._parse_json(
self._search_regex(
r'(?s)jwsetup\s*=\s*({.+?})\s*;', webpage, 'jwsetup',
default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if jwsetup:
info = self._parse_jwplayer_data(
jwsetup, video_id, require_title=False, m3u8_id='hls',
base_url=url)
add_referer(info['formats'])
ld_info = self._search_json_ld(webpage, video_id, default={})
return merge_dicts(info, ld_info)
# Obsolete
# We first look for clipid, because clipprog always appears before # We first look for clipid, because clipprog always appears before
patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')] patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
results = list(filter(None, (re.search(p, webpage) for p in patterns))) results = list(filter(None, (re.search(p, webpage) for p in patterns)))
@ -165,8 +187,7 @@ class CSpanIE(InfoExtractor):
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
path, video_id, 'mp4', entry_protocol='m3u8_native', path, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }] m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
for f in formats: add_referer(formats)
f.setdefault('http_headers', {})['Referer'] = url
self._sort_formats(formats) self._sort_formats(formats)
entries.append({ entries.append({
'id': '%s_%d' % (video_id, partnum + 1), 'id': '%s_%d' % (video_id, partnum + 1),