# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class FazIE(InfoExtractor):
IE_NAME = u'faz.net'
- _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html'
+ _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
_TEST = {
u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
webpage = self._download_webpage(url, video_id)
config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
u'config xml url')
- config_xml = self._download_webpage(config_xml_url, video_id,
+ config = self._download_xml(config_xml_url, video_id,
u'Downloading config xml')
- config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
encodings = config.find('ENCODINGS')
formats = []
})
descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
- info = {
+ return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': descr,
'thumbnail': config.find('STILL/STILL_BIG').text,
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info