fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[izlesene] Fix extraction (closes #16233)

This commit is contained in:
Enes 2018-04-24 22:48:40 +03:00 committed by Sergey M․
parent aee36ca832
commit f4d261b765
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 10 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/izlesene.py
View File

@ -1,8 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..utils import ( from ..utils import (
@ -72,7 +70,7 @@ class IzleseneIE(InfoExtractor):
'uploadDate', webpage, 'upload date')) 'uploadDate', webpage, 'upload date'))
duration = float_or_none(self._html_search_regex( duration = float_or_none(self._html_search_regex(
r'"videoduration"\s*:\s*"([^"]+)"', r'videoduration\s*=\s*\'([^\']+)\'',
webpage, 'duration', fatal=False), scale=1000) webpage, 'duration', fatal=False), scale=1000)
view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
@ -80,29 +78,18 @@ class IzleseneIE(InfoExtractor):
r'comment_count\s*=\s*\'([^\']+)\';', r'comment_count\s*=\s*\'([^\']+)\';',
webpage, 'comment_count', fatal=False) webpage, 'comment_count', fatal=False)
content_url = self._html_search_meta( streams_json = self._html_search_regex(
'contentURL', webpage, 'content URL', fatal=False) r'_videoObj\s*=\s*(.+);', webpage, 'streams')
ext = determine_ext(content_url, 'mp4') streams = self._parse_json(streams_json, video_id)
# Might be empty for some videos.
streams = self._html_search_regex(
r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
formats = [] formats = []
if streams: for stream in streams.get('media').get('level'):
for stream in streams.split('|'): url = stream.get('source')
quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() ext = determine_ext(url, 'mp4')
formats.append({ quality = stream.get('value')
'format_id': '%sp' % quality if quality else 'sd',
'url': compat_urllib_parse_unquote(url),
'ext': ext,
})
else:
stream_url = self._search_regex(
r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
formats.append({ formats.append({
'format_id': 'sd', 'format_id': '%sp' % quality,
'url': compat_urllib_parse_unquote(stream_url), 'url': compat_urllib_parse_unquote(url),
'ext': ext, 'ext': ext,
}) })