debian/changelog: Annotate bugs to close.

[youtubedl] / youtube_dl / extractor / yam.py

diff --git a/youtube_dl/extractor/yam.py b/youtube_dl/extractor/yam.py
index b294767c5b6bc5a7ec918e9108cc4cff1a5fac40..9d851bae3b779d8ce434742d6f5ef70d3f423936 100644 (file)
--- a/youtube_dl/extractor/yam.py
+++ b/youtube_dl/extractor/yam.py
@@ -8,6 +8,8 @@ from ..compat import compat_urlparse
 from ..utils import (
     float_or_none,
     month_by_abbreviation,
 from ..utils import (
     float_or_none,
     month_by_abbreviation,

+    ExtractorError,
+    get_element_by_attribute,

 )
 
 
 )
 
 


@@ -22,22 +24,49 @@ class YamIE(InfoExtractor):
             'id': '2283921',
             'ext': 'mp3',
             'title': '發現 - 趙薇 京華煙雲主題曲',
             'id': '2283921',
             'ext': 'mp3',
             'title': '發現 - 趙薇 京華煙雲主題曲',

+            'description': '發現 - 趙薇 京華煙雲主題曲',

             'uploader_id': 'princekt',
             'upload_date': '20080807',
             'duration': 313.0,
         }
     }, {
         # An external video hosted on YouTube
             'uploader_id': 'princekt',
             'upload_date': '20080807',
             'duration': 313.0,
         }
     }, {
         # An external video hosted on YouTube

-        'url': 'http://mymedia.yam.com/m/3598173',
-        'md5': '0238ceec479c654e8c2f1223755bf3e9',
+        'url': 'http://mymedia.yam.com/m/3599430',
+        'md5': '03127cf10d8f35d120a9e8e52e3b17c6',

         'info_dict': {
         'info_dict': {

-            'id': 'pJ2Deys283c',
+            'id': 'CNpEoQlrIgA',

             'ext': 'mp4',
             'ext': 'mp4',

-            'upload_date': '20150202',
+            'upload_date': '20150306',

             'uploader': '新莊社大瑜伽社',
             'uploader': '新莊社大瑜伽社',

-            'description': 'md5:f5cc72f0baf259a70fb731654b0d2eff',
+            'description': 'md5:11e2e405311633ace874f2e6226c8b17',

             'uploader_id': '2323agoy',
             'uploader_id': '2323agoy',

-            'title': '外婆的澎湖灣KTV-潘安邦',
+            'title': '20090412陽明山二子坪-1',
+        },
+        'skip': 'Video does not exist',
+    }, {
+        'url': 'http://mymedia.yam.com/m/3598173',
+        'info_dict': {
+            'id': '3598173',
+            'ext': 'mp4',
+        },
+        'skip': 'cause Yam system error',
+    }, {
+        'url': 'http://mymedia.yam.com/m/3599437',
+        'info_dict': {
+            'id': '3599437',
+            'ext': 'mp4',
+        },
+        'skip': 'invalid YouTube URL',
+    }, {
+        'url': 'http://mymedia.yam.com/m/2373534',
+        'md5': '7ff74b91b7a817269d83796f8c5890b1',
+        'info_dict': {
+            'id': '2373534',
+            'ext': 'mp3',
+            'title': '林俊傑&蔡卓妍-小酒窩',
+            'description': 'md5:904003395a0fcce6cfb25028ff468420',
+            'upload_date': '20080928',
+            'uploader_id': 'onliner2',

         }
     }]
 
         }
     }]
 


@@ -45,6 +74,13 @@ class YamIE(InfoExtractor):
         video_id = self._match_id(url)
         page = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         page = self._download_webpage(url, video_id)
 

+        # Check for errors
+        system_msg = self._html_search_regex(
+            r'系統訊息(?:<br>|\n|\r)*([^<>]+)<br>', page, 'system message',
+            default=None)
+        if system_msg:
+            raise ExtractorError(system_msg, expected=True)
+

         # Is it hosted externally on YouTube?
         youtube_url = self._html_search_regex(
             r'<embed src="(http://www.youtube.com/[^"]+)"',
         # Is it hosted externally on YouTube?
         youtube_url = self._html_search_regex(
             r'<embed src="(http://www.youtube.com/[^"]+)"',


@@ -52,15 +88,19 @@ class YamIE(InfoExtractor):
         if youtube_url:
             return self.url_result(youtube_url, 'Youtube')
 
         if youtube_url:
             return self.url_result(youtube_url, 'Youtube')
 

+        title = self._html_search_regex(
+            r'<h1[^>]+class="heading"[^>]*>\s*(.+)\s*</h1>', page, 'title')
+

         api_page = self._download_webpage(
             'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
             note='Downloading API page')
         api_result_obj = compat_urlparse.parse_qs(api_page)
 
         api_page = self._download_webpage(
             'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
             note='Downloading API page')
         api_result_obj = compat_urlparse.parse_qs(api_page)
 

+        info_table = get_element_by_attribute('class', 'info', page)

         uploader_id = self._html_search_regex(
         uploader_id = self._html_search_regex(

-            r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z]+)"',
-            page, 'uploader id', fatal=False)
-        mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2})  ' +
+            r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z0-9]+)"',
+            info_table, 'uploader id', fatal=False)
+        mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2})\s+' +

                          r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
         if mobj:
             upload_date = '%s%02d%02d' % (
                          r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
         if mobj:
             upload_date = '%s%02d%02d' % (


@@ -74,7 +114,8 @@ class YamIE(InfoExtractor):
         return {
             'id': video_id,
             'url': api_result_obj['mp3file'][0],
         return {
             'id': video_id,
             'url': api_result_obj['mp3file'][0],

-            'title': self._html_search_meta('description', page),
+            'title': title,
+            'description': self._html_search_meta('description', page),

             'duration': duration,
             'uploader_id': uploader_id,
             'upload_date': upload_date,
             'duration': duration,
             'uploader_id': uploader_id,
             'upload_date': upload_date,