depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 01:08:10 +00:00
Code Issues Releases Wiki Activity

[bild] extract info from json request

Browse source
This commit is contained in:
remitamine 2015-10-10 00:45:23 +01:00 committed by Sergey M․
parent 7c84562945
commit 70cb4d51c9
1 changed files with 8 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
youtube_dl/extractor/bild.py
View file

@ -4,7 +4,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
fix_xml_ampersands, unescapeHTML,
) )
@ -17,7 +17,7 @@ class BildIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '38184146', 'id': '38184146',
'ext': 'mp4', 'ext': 'mp4',
'title': 'BILD hat sie getestet', 'title': 'Das können die neuen iPads ',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'duration': 196, 'duration': 196,
'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ', 'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
@ -27,16 +27,13 @@ class BildIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml" video_data = self._download_json(url.split(".bild.html")[0] + ",view=json.bild.html", video_id)
doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
duration = int_or_none(doc.attrib.get('duration'), scale=1000)
return { return {
'id': video_id, 'id': video_id,
'title': doc.attrib['ueberschrift'], 'title': unescapeHTML(video_data['title']),
'description': doc.attrib.get('text'), 'description': unescapeHTML(video_data.get('description')),
'url': doc.attrib['src'], 'url': video_data['clipList'][0]['srces'][0]['src'],
'thumbnail': doc.attrib.get('img'), 'thumbnail': video_data.get('poster'),
'duration': duration, 'duration': int_or_none(video_data.get('durationSec')),
} }