debian/control: Mark compliance with Debian policy 4.1.5.

[youtubedl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index 08257147ef5abba46224190b9d8c32ab280182bf..e49b233f2b98ebf5cf559e9e80d8a06a0687381f 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -16,6 +16,7 @@ from ..utils import (
     ExtractorError,
     InAdvancePagedList,
     int_or_none,
     ExtractorError,
     InAdvancePagedList,
     int_or_none,

+    merge_dicts,

     NO_DEFAULT,
     RegexNotFoundError,
     sanitized_Request,
     NO_DEFAULT,
     RegexNotFoundError,
     sanitized_Request,


@@ -36,7 +37,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
     _LOGIN_URL = 'https://vimeo.com/log_in'
 
     def _login(self):
     _LOGIN_URL = 'https://vimeo.com/log_in'
 
     def _login(self):

-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()

         if username is None:
             if self._LOGIN_REQUIRED:
                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
         if username is None:
             if self._LOGIN_REQUIRED:
                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)


@@ -538,9 +539,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 # We try to find out to which variable is assigned the config dic
                 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
                 if m_variable_name is not None:
                 # We try to find out to which variable is assigned the config dic
                 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
                 if m_variable_name is not None:

-                    config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
+                    config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]

                 else:
                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
                 else:
                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']

+                config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')

                 config = self._search_regex(config_re, webpage, 'info section',
                                             flags=re.DOTALL)
                 config = json.loads(config)
                 config = self._search_regex(config_re, webpage, 'info section',
                                             flags=re.DOTALL)
                 config = json.loads(config)


@@ -639,16 +641,18 @@ class VimeoIE(VimeoBaseInfoExtractor):
                             'preference': 1,
                         })
 
                             'preference': 1,
                         })
 

-        info_dict = self._parse_config(config, video_id)
-        formats.extend(info_dict['formats'])
+        info_dict_config = self._parse_config(config, video_id)
+        formats.extend(info_dict_config['formats'])

         self._vimeo_sort_formats(formats)
 
         self._vimeo_sort_formats(formats)
 

+        json_ld = self._search_json_ld(webpage, video_id, default={})
+

         if not cc_license:
             cc_license = self._search_regex(
                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
                 webpage, 'license', default=None, group='license')
 
         if not cc_license:
             cc_license = self._search_regex(
                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
                 webpage, 'license', default=None, group='license')
 

-        info_dict.update({
+        info_dict = {

             'id': video_id,
             'formats': formats,
             'timestamp': unified_timestamp(timestamp),
             'id': video_id,
             'formats': formats,
             'timestamp': unified_timestamp(timestamp),


@@ -658,7 +662,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'like_count': like_count,
             'comment_count': comment_count,
             'license': cc_license,
             'like_count': like_count,
             'comment_count': comment_count,
             'license': cc_license,

-        })
+        }
+
+        info_dict = merge_dicts(info_dict, info_dict_config, json_ld)

 
         return info_dict
 
 
         return info_dict
 


@@ -984,10 +990,10 @@ class VimeoWatchLaterIE(VimeoChannelIE):
 
 
 class VimeoLikesIE(InfoExtractor):
 
 
 class VimeoLikesIE(InfoExtractor):

-    _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+    _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'

     IE_NAME = 'vimeo:likes'
     IE_DESC = 'Vimeo user likes'
     IE_NAME = 'vimeo:likes'
     IE_DESC = 'Vimeo user likes'

-    _TEST = {
+    _TESTS = [{

         'url': 'https://vimeo.com/user755559/likes/',
         'playlist_mincount': 293,
         'info_dict': {
         'url': 'https://vimeo.com/user755559/likes/',
         'playlist_mincount': 293,
         'info_dict': {


@@ -995,7 +1001,10 @@ class VimeoLikesIE(InfoExtractor):
             'description': 'See all the videos urza likes',
             'title': 'Videos urza likes',
         },
             'description': 'See all the videos urza likes',
             'title': 'Videos urza likes',
         },

-    }
+    }, {
+        'url': 'https://vimeo.com/stormlapse/likes',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         user_id = self._match_id(url)
 
     def _real_extract(self, url):
         user_id = self._match_id(url)


@@ -1004,7 +1013,7 @@ class VimeoLikesIE(InfoExtractor):
             self._search_regex(
                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
                     .*?</a></li>\s*<li\s+class="pagination_next">
             self._search_regex(
                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
                     .*?</a></li>\s*<li\s+class="pagination_next">

-                ''', webpage, 'page count'),
+                ''', webpage, 'page count', default=1),

             'page count', fatal=True)
         PAGE_SIZE = 12
         title = self._html_search_regex(
             'page count', fatal=True)
         PAGE_SIZE = 12
         title = self._html_search_regex(


@@ -1012,7 +1021,7 @@ class VimeoLikesIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
 
         def _get_page(idx):
         description = self._html_search_meta('description', webpage)
 
         def _get_page(idx):

-            page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+            page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (

                 user_id, idx + 1)
             webpage = self._download_webpage(
                 page_url, user_id,
                 user_id, idx + 1)
             webpage = self._download_webpage(
                 page_url, user_id,


@@ -1032,7 +1041,7 @@ class VimeoLikesIE(InfoExtractor):
 
         return {
             '_type': 'playlist',
 
         return {
             '_type': 'playlist',

-            'id': 'user%s_likes' % user_id,
+            'id': '%s_likes' % user_id,

             'title': title,
             'description': description,
             'entries': pl,
             'title': title,
             'description': description,
             'entries': pl,