about summary refs log tree commit diff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2017-01-22 02:06:34 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2017-01-22 02:06:34 +0800
commit7c20b7484cc91a4818a98ca8d5b7ef94d5c38fb8 (patch)
treeb11dda724e19803cc9f61f56bd88b80d457b0c32
parent04a3d4d23472ffa4a482d8ebf2d8fdbb3e974327 (diff)
downloadyoutube-dl-7c20b7484cc91a4818a98ca8d5b7ef94d5c38fb8.tar.gz
youtube-dl-7c20b7484cc91a4818a98ca8d5b7ef94d5c38fb8.tar.xz
youtube-dl-7c20b7484cc91a4818a98ca8d5b7ef94d5c38fb8.zip
[nextmedia] Support redirected URLs
-rw-r--r--ChangeLog1
-rw-r--r--youtube_dl/extractor/nextmedia.py13
2 files changed, 13 insertions, 1 deletions
diff --git a/ChangeLog b/ChangeLog
index 217971ec6..00c8a063f 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,6 +1,7 @@
 version <unreleased>
 
 Extractors
++ [nextmedia] Support redirected URLs
 + [cspan] Support Ustream embedded videos (#11547)
 
 
diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py
index c900f232a..626ed8b49 100644
--- a/youtube_dl/extractor/nextmedia.py
+++ b/youtube_dl/extractor/nextmedia.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import parse_iso8601
 
 
@@ -30,6 +31,12 @@ class NextMediaIE(InfoExtractor):
         return self._extract_from_nextmedia_page(news_id, url, page)
 
     def _extract_from_nextmedia_page(self, news_id, url, page):
+        redirection_url = self._search_regex(
+            r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
+            page, 'redirection URL', default=None, group='url')
+        if redirection_url:
+            return self.url_result(compat_urlparse.urljoin(url, redirection_url))
+
         title = self._fetch_title(page)
         video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
 
@@ -93,7 +100,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -157,6 +164,10 @@ class AppleDailyIE(NextMediaIE):
     }, {
         'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
         'only_matching': True,
+    }, {
+        # Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
+        'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
+        'only_matching': True,
     }]
 
     _URL_PATTERN = r'\{url: \'(.+)\'\}'