dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[bild] Simplify (#3983)

This commit is contained in:
Philipp Hagemeister 2014-10-24 15:09:43 +02:00
parent 8d81f872fb
commit b5a14350b9
1 changed files with 39 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/bild.py
View File

@ -1,46 +1,39 @@
#coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none
class BildIE(InfoExtractor): class BildIE(InfoExtractor):
IE_NAME = 'bild' _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
IE_DESC = 'Bild.de'
_TEST = { _TEST = {
'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html', 'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
'md5': 'dd495cbd99f2413502a1713a1156ac8a',
'info_dict': { 'info_dict': {
'id': '38184146', 'id': '38184146',
'ext': 'mp4',
'title': 'BILD hat sie getestet', 'title': 'BILD hat sie getestet',
'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg', 'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.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. ',
} }
} }
#http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html
_VALID_URL = r'http?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = m.group('id')
#webpage = self._download_webpage(url, video_id)
xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml" xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
doc = self._download_xml(xml_url, video_id) doc = self._download_xml(xml_url, video_id)
video_url = doc.attrib['src'] duration = int_or_none(doc.attrib.get('duration'), scale=1000)
title = doc.attrib['ueberschrift']
description = doc.attrib['text']
thumbnail = doc.attrib['img']
duration = int(doc.attrib['duration'])/1000
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': doc.attrib['ueberschrift'],
'description': description, 'description': doc.attrib.get('text'),
'url': video_url, 'url': doc.attrib['src'],
'thumbnail': thumbnail, 'thumbnail': doc.attrib.get('img'),
'duration': duration, 'duration': duration,
} }