X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/54477c858fa2504360964e675faf953d78ac57e6..63a6927374492ef47c8fd6de67d0760ace4dd0ed:/youtube_dl/extractor/faz.py diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index deaa4ed..c6ab695 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -1,18 +1,15 @@ # encoding: utf-8 import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( determine_ext, - clean_html, - get_element_by_attribute, ) class FazIE(InfoExtractor): IE_NAME = u'faz.net' - _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P\d+).html' + _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P\d+)\.html' _TEST = { u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', @@ -30,9 +27,8 @@ class FazIE(InfoExtractor): 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 = [] @@ -47,14 +43,11 @@ class FazIE(InfoExtractor): 'format_id': code.lower(), }) - descr_html = get_element_by_attribute('class', 'Content Copy', webpage) - info = { + descr = self._html_search_regex(r'

(.*?)

', webpage, u'description') + return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': clean_html(descr_html), + 'description': descr, 'thumbnail': config.find('STILL/STILL_BIG').text, } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info