pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-16 18:42:38 +09:00
Code Issues Projects Releases Wiki Activity

[clipfish] improve info extraction

Browse Source
This commit is contained in:
remitamine 2015-10-30 20:06:38 +01:00
parent 6722ebd437
commit 240384afe6
1 changed files with 21 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/clipfish.py
View File

@ -4,11 +4,8 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
int_or_none, int_or_none,
js_to_json, unified_strdate,
parse_iso8601,
remove_end,
) )
@ -21,48 +18,37 @@ class ClipfishIE(InfoExtractor):
'id': '3966754', 'id': '3966754',
'ext': 'mp4', 'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer', 'title': 'FIFA 14 - E3 2013 Trailer',
'timestamp': 1370938118, 'description': 'Video zu FIFA 14: E3 2013 Trailer',
'upload_date': '20130611', 'upload_date': '20130611',
'duration': 82, 'duration': 82,
'view_count': int,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) video_info = self._download_json('http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id, video_id)['items'][0]
video_info = self._parse_json( formats = [{
js_to_json(self._html_search_regex( 'url': video_info['media_videourl_hls'].replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
'(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
video_id)
formats = []
for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
ext = determine_ext(video_url)
if ext == 'm3u8':
formats.append({
'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
'ext': 'mp4', 'ext': 'mp4',
'format_id': 'hls', 'format_id': 'hls',
}) },{
else: 'url': video_info['media_videourl'],
formats.append({ 'format_id': 'mp4',
'url': video_url, 'width': int_or_none(video_info.get('width')),
'format_id': ext, 'height': int_or_none(video_info.get('height')),
}) 'tbr': int_or_none(video_info.get('bitrate')),
self._sort_formats(formats) }]
title = remove_end(self._og_search_title(webpage), ' - Video')
thumbnail = self._og_search_thumbnail(webpage)
duration = int_or_none(video_info.get('length'))
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': video_info['title'],
'description': video_info.get('descr'),
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
'duration': duration, 'duration': int_or_none(video_info.get('media_length')),
'timestamp': timestamp, 'upload_date': unified_strdate(video_info.get('pubDate')),
'view_count': int_or_none(video_info.get('media_views'))
} }