[faz] Modernize

youtube_dl/extractor/faz.py

@@ -1,5 +1,5 @@
 # encoding: utf-8
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
@@ -8,42 +8,44 @@ from ..utils import (
 
 
 class FazIE(InfoExtractor):
-    IE_NAME = u'faz.net'
+    IE_NAME = 'faz.net'
     _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',
+        'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
-        u'file': u'12610585.mp4',
+        'info_dict': {
-        u'info_dict': {
+            'id': '12610585',
-            u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
+            'ext': 'mp4',
-            u'description': u'md5:1453fbf9a0d041d985a47306192ea253',
+            'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
+            'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
+
-        self.to_screen(video_id)
         webpage = self._download_webpage(url, video_id)
-        config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
+        config_xml_url = self._search_regex(
-            u'config xml url')
+            r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
-        config = self._download_xml(config_xml_url, video_id,
+        config = self._download_xml(
-            u'Downloading config xml')
+            config_xml_url, video_id, 'Downloading config xml')
 
         encodings = config.find('ENCODINGS')
         formats = []
-        for code in ['LOW', 'HIGH', 'HQ']:
+        for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
             encoding = encodings.find(code)
             if encoding is None:
                 continue
             encoding_url = encoding.find('FILENAME').text
             formats.append({
                 'url': encoding_url,
-                'ext': determine_ext(encoding_url),
                 'format_id': code.lower(),
+                'quality': pref,
             })
+        self._sort_formats(formats)
 
-        descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+        descr = self._html_search_regex(
+            r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),