gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[izlesene] Improve extraction and fix issues (closes #16407, closes #16271)

Browse source
This commit is contained in:
Sergey M․ 2018-05-26 01:51:38 +07:00
parent f4d261b765
commit 03fad17cb6
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 32 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
youtube_dl/extractor/izlesene.py
View file

@ -2,7 +2,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
float_or_none, float_or_none,
@ -55,12 +58,33 @@ class IzleseneIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
url = 'http://www.izlesene.com/video/%s' % video_id webpage = self._download_webpage('http://www.izlesene.com/video/%s' % video_id, video_id)
webpage = self._download_webpage(url, video_id)
video = self._parse_json(
self._search_regex(
r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'),
video_id)
title = video.get('videoTitle') or self._og_search_title(webpage)
formats = []
for stream in video['media']['level']:
source_url = stream.get('source')
if not source_url or not isinstance(source_url, compat_str):
continue
ext = determine_ext(url, 'mp4')
quality = stream.get('value')
height = int_or_none(quality)
formats.append({
'format_id': '%sp' % quality if quality else 'sd',
'url': compat_urllib_parse_unquote(source_url),
'ext': ext,
'height': height,
})
self._sort_formats(formats)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage, default=None) description = self._og_search_description(webpage, default=None)
thumbnail = self._proto_relative_url( thumbnail = video.get('posterURL') or self._proto_relative_url(
self._og_search_thumbnail(webpage), scheme='http:') self._og_search_thumbnail(webpage), scheme='http:')
uploader = self._html_search_regex( uploader = self._html_search_regex(
@ -69,30 +93,15 @@ class IzleseneIE(InfoExtractor):
timestamp = parse_iso8601(self._html_search_meta( timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date')) 'uploadDate', webpage, 'upload date'))
duration = float_or_none(self._html_search_regex( duration = float_or_none(video.get('duration') or self._html_search_regex(
r'videoduration\s*=\s*\'([^\']+)\'', r'videoduration["\']?\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'duration', fatal=False), scale=1000) webpage, 'duration', fatal=False, group='value'), scale=1000)
view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
comment_count = self._html_search_regex( comment_count = self._html_search_regex(
r'comment_count\s*=\s*\'([^\']+)\';', r'comment_count\s*=\s*\'([^\']+)\';',
webpage, 'comment_count', fatal=False) webpage, 'comment_count', fatal=False)
streams_json = self._html_search_regex(
r'_videoObj\s*=\s*(.+);', webpage, 'streams')
streams = self._parse_json(streams_json, video_id)
formats = []
for stream in streams.get('media').get('level'):
url = stream.get('source')
ext = determine_ext(url, 'mp4')
quality = stream.get('value')
formats.append({
'format_id': '%sp' % quality,
'url': compat_urllib_parse_unquote(url),
'ext': ext,
})
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,