debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / expressen.py

diff --git a/youtube_dl/extractor/expressen.py b/youtube_dl/extractor/expressen.py
index f61178012feb4db017e3c96f18ec4959ac3f4f42..f79365038d973754ee0a2a398bc035d9521b2a6d 100644 (file)
--- a/youtube_dl/extractor/expressen.py
+++ b/youtube_dl/extractor/expressen.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -11,7 +13,13 @@ from ..utils import (
 
 
 class ExpressenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?expressen\.se/
+                        (?:(?:tvspelare/video|videoplayer/embed)/)?
+                        tv/(?:[^/]+/)*
+                        (?P<id>[^/?#&]+)
+                    '''
     _TESTS = [{
         'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
         'md5': '2fbbe3ca14392a6b1b36941858d33a45',
@@ -28,8 +36,21 @@ class ExpressenIE(InfoExtractor):
     }, {
         'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.expressen.se/tvspelare/video/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url') for mobj in re.finditer(
+                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1',
+                webpage)]
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
@@ -61,8 +82,8 @@ class ExpressenIE(InfoExtractor):
         title = info.get('titleRaw') or data['title']
         description = info.get('descriptionRaw')
         thumbnail = info.get('socialMediaImage') or data.get('image')
-        duration = int_or_none(info.get('videoTotalSecondsDuration') or
-                               data.get('totalSecondsDuration'))
+        duration = int_or_none(info.get('videoTotalSecondsDuration')
+                               or data.get('totalSecondsDuration'))
         timestamp = unified_timestamp(info.get('publishDate'))
 
         return {