]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/faz.py
Merge tag 'upstream/2016.12.01'
[youtubedl] / youtube_dl / extractor / faz.py
index 3c39ca451a38e69a822968911e758847657380e9..4bc8fc5127010e1b3ced207da04f8926716cc94d 100644 (file)
@@ -1,14 +1,19 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    xpath_element,
+    xpath_text,
+    int_or_none,
+)
 
 
 class FazIE(InfoExtractor):
     IE_NAME = 'faz.net'
 
 
 class FazIE(InfoExtractor):
     IE_NAME = 'faz.net'
-    _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
         'info_dict': {
             'id': '12610585',
         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
         'info_dict': {
             'id': '12610585',
@@ -16,37 +21,53 @@ class FazIE(InfoExtractor):
             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
-    }
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/foobarblafasel-13659345.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+        description = self._og_search_description(webpage)
         config_xml_url = self._search_regex(
         config_xml_url = self._search_regex(
-            r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
+            r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
         config = self._download_xml(
             config_xml_url, video_id, 'Downloading config xml')
 
         config = self._download_xml(
             config_xml_url, video_id, 'Downloading config xml')
 
-        encodings = config.find('ENCODINGS')
+        encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
         formats = []
         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
         formats = []
         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,
-                'format_id': code.lower(),
-                'quality': pref,
-            })
+            encoding = xpath_element(encodings, code)
+            if encoding is not None:
+                encoding_url = xpath_text(encoding, 'FILENAME')
+                if encoding_url:
+                    formats.append({
+                        'url': encoding_url,
+                        'format_id': code.lower(),
+                        'quality': pref,
+                        'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
+                    })
         self._sort_formats(formats)
 
         self._sort_formats(formats)
 
-        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),
             'formats': formats,
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),
             'formats': formats,
-            'description': descr,
-            'thumbnail': config.find('STILL/STILL_BIG').text,
+            'description': description.strip() if description else None,
+            'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
+            'duration': int_or_none(xpath_text(config, 'DURATION')),
         }
         }