ansol/youtube-dl
7
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-19 03:25:13 +00:00
Code Issues Projects Releases Wiki Activity

[njpwworld] Fix extraction (closes #13162)

Browse Source
This commit is contained in:
Sergey M․ 2017-05-19 23:11:02 +07:00
parent 5f6fbcea08
commit 8fffac6927
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/njpwworld.py
View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
extract_attributes,
get_element_by_class, get_element_by_class,
urlencode_postdata, urlencode_postdata,
) )
@ -56,17 +57,24 @@ class NJPWWorldIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
formats = [] formats = []
for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage): for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
player_url = compat_urlparse.urljoin(url, player_url) player = extract_attributes(mobj.group(0))
player_path = player.get('href')
if not player_path:
continue
kind = self._search_regex(
r'(low|high)$', player.get('class') or '', 'kind',
default='low')
player_url = compat_urlparse.urljoin(url, player_path)
player_page = self._download_webpage( player_page = self._download_webpage(
player_url, video_id, note='Downloading player page') player_url, video_id, note='Downloading player page')
entries = self._parse_html5_media_entries( entries = self._parse_html5_media_entries(
player_url, player_page, video_id, m3u8_id='hls-%s' % kind, player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
m3u8_entry_protocol='m3u8_native', m3u8_entry_protocol='m3u8_native')
preference=2 if 'hq' in kind else 1) kind_formats = entries[0]['formats']
formats.extend(entries[0]['formats']) for f in kind_formats:
f['quality'] = 2 if kind == 'high' else 1
formats.extend(kind_formats)
self._sort_formats(formats) self._sort_formats(formats)