[extractors] Use http_headers for setting the User-Agent and the Referer

[youtube-dl] / youtube_dl / extractor / wdr.py

diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index f741ba54007737e132f327178be283a478b6527f..313b9c15ddc576c226e1f4b8ee211bc816e2ebe9 100644 (file)
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,12 +1,15 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_parse_qs,
     compat_urlparse,
+)
+from ..utils import (
     determine_ext,
     unified_strdate,
 )
@@ -55,16 +58,20 @@ class WDRIE(InfoExtractor):
             },
         },
         {
-            'url': 'http://www.funkhauseuropa.de/av/audiosuepersongsoulbossanova100-audioplayer.html',
-            'md5': '24e83813e832badb0a8d7d1ef9ef0691',
+            'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+            'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
             'info_dict': {
-                'id': 'mdb-463528',
+                'id': 'mdb-478135',
                 'ext': 'mp3',
-                'title': 'Süpersong: Soul Bossa Nova',
+                'title': 'Flavia Coelho: Amar é Amar',
                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
-                'upload_date': '20140630',
+                'upload_date': '20140717',
             },
         },
+        {
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
+            'playlist_mincount': 146,
+        }
     ]
 
     def _real_extract(self, url):
@@ -79,9 +86,30 @@ class WDRIE(InfoExtractor):
                 self.url_result(page_url + href, 'WDR')
                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
             ]
+
+            if entries:  # Playlist page
+                return self.playlist_result(entries, page_id)
+
+            # Overview page
+            entries = []
+            for page_num in itertools.count(2):
+                hrefs = re.findall(
+                    r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
+                    webpage)
+                entries.extend(
+                    self.url_result(page_url + href, 'WDR')
+                    for href in hrefs)
+                next_url_m = re.search(
+                    r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
+                if not next_url_m:
+                    break
+                next_url = page_url + next_url_m.group(1)
+                webpage = self._download_webpage(
+                    next_url, page_id,
+                    note='Downloading playlist page %d' % page_num)
             return self.playlist_result(entries, page_id)
 
-        flashvars = compat_urlparse.parse_qs(
+        flashvars = compat_parse_qs(
             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 
         page_id = flashvars['trackerClipId'][0]
@@ -141,8 +169,9 @@ class WDRMobileIE(InfoExtractor):
             'title': mobj.group('title'),
             'age_limit': int(mobj.group('age_limit')),
             'url': url,
-            'ext': determine_ext(url),
-            'user_agent': 'mobile',
+            'http_headers': {
+                'User-Agent': 'mobile',
+            },
         }
 
 
@@ -171,8 +200,7 @@ class WDRMausIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         param_code = self._html_search_regex(
@@ -223,5 +251,3 @@ class WDRMausIE(InfoExtractor):
             'thumbnail': thumbnail,
             'upload_date': upload_date,
         }
-
-# TODO test _1
\ No newline at end of file