Merge tag 'upstream/2016.12.01'

[youtubedl] / youtube_dl / extractor / nextmedia.py

diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py
index 02dba4ef639e64deff790f94bd5cd0cd6da2a4cb..dee9056d39e9bb0076d390054006c6dd4246afae 100644 (file)
--- a/youtube_dl/extractor/nextmedia.py
+++ b/youtube_dl/extractor/nextmedia.py
@@ -6,7 +6,8 @@ from ..utils import parse_iso8601
 
 
 class NextMediaIE(InfoExtractor):
-    _VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
+    IE_DESC = '蘋果日報'
+    _VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
         'md5': 'dff9fad7009311c421176d1ac90bfe4f',
@@ -66,7 +67,8 @@ class NextMediaIE(InfoExtractor):
 
 
 class NextMediaActionNewsIE(NextMediaIE):
-    _VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
+    IE_DESC = '蘋果日報 - 動新聞'
+    _VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
     _TESTS = [{
         'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
         'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
@@ -89,8 +91,9 @@ class NextMediaActionNewsIE(NextMediaIE):
         return self._extract_from_nextmedia_page(news_id, url, article_page)
 
 
-class AppleDailyRealtimeNewsIE(NextMediaIE):
-    _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+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+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -99,7 +102,7 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
             'ext': 'mp4',
             'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:b23787119933404ce515c6356a8c355c',
+            'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4',
             'upload_date': '20150128',
         }
     }, {
@@ -110,26 +113,10 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
             'ext': 'mp4',
             'title': '不滿被踩腳　山東兩大媽一路打下車',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d',
+            'description': 'md5:175b4260c1d7c085993474217e4ab1b4',
             'upload_date': '20150128',
         }
-    }]
-
-    _URL_PATTERN = r'\{url: \'(.+)\'\}'
-
-    def _fetch_title(self, page):
-        return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title')
-
-    def _fetch_thumbnail(self, page):
-        return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
-
-    def _fetch_timestamp(self, page):
-        return None
-
-
-class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
-    _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
-    _TESTS = [{
+    }, {
         'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
         'md5': '03df296d95dedc2d5886debbb80cb43f',
         'info_dict': {
@@ -139,7 +126,8 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
             'thumbnail': 're:^https?://.*\.jpg$',
             'description': 'md5:23c0aac567dc08c9c16a3161a2c2e3cd',
             'upload_date': '20150128',
-        }
+        },
+        'skip': 'redirect to http://www.appledaily.com.tw/animation/',
     }, {
         # No thumbnail
         'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003673/',
@@ -153,11 +141,35 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
         },
         'expected_warnings': [
             'video thumbnail',
-        ]
+        ],
+        'skip': 'redirect to http://www.appledaily.com.tw/animation/',
+    }, {
+        'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/',
+        'md5': 'eaa20e6b9df418c912d7f5dec2ba734d',
+        'info_dict': {
+            'id': '35770334',
+            'ext': 'mp4',
+            'title': '咖啡占卜測 XU裝熟指數',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
+            'upload_date': '20140417',
+        },
+    }, {
+        'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
+        'only_matching': True,
     }]
 
+    _URL_PATTERN = r'\{url: \'(.+)\'\}'
+
     def _fetch_title(self, page):
-        return self._html_search_meta('description', page, 'news title')
+        return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or
+                self._html_search_meta('description', page, 'news title'))
+
+    def _fetch_thumbnail(self, page):
+        return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
+
+    def _fetch_timestamp(self, page):
+        return None
 
     def _fetch_description(self, page):
         return self._html_search_meta('description', page, 'news description')