]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/faz.py
Merge tag 'upstream/2013.12.23'
[youtubedl] / youtube_dl / extractor / faz.py
index deaa4ed2d9bc14406b6a7d3d6e8b015c6fcf915d..c6ab6952e84dc9074816f28ebb7fe6d8ce02cb47 100644 (file)
@@ -1,18 +1,15 @@
 # encoding: utf-8
 import re
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
 
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    clean_html,
-    get_element_by_attribute,
 )
 
 
 class FazIE(InfoExtractor):
     IE_NAME = u'faz.net'
 )
 
 
 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',
 
     _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')
         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')
             u'Downloading config xml')
-        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
 
         encodings = config.find('ENCODINGS')
         formats = []
 
         encodings = config.find('ENCODINGS')
         formats = []
@@ -47,14 +43,11 @@ class FazIE(InfoExtractor):
                 'format_id': code.lower(),
             })
 
                 'format_id': code.lower(),
             })
 
-        descr_html = get_element_by_attribute('class', 'Content Copy', webpage)
-        info = {
+        descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+        return {
             'id': video_id,
             'title': self._og_search_title(webpage),
             'formats': formats,
             '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,
         }
             'thumbnail': config.find('STILL/STILL_BIG').text,
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info