From d6e6a4225650ff220c7fe0687d883552e4b45bde Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 28 Sep 2014 12:14:16 +0200 Subject: [PATCH] [vimeo:likes] Add new extractor (Fixes #3835) --- test/test_download.py | 4 +++- youtube_dl/extractor/__init__.py | 5 +++-- youtube_dl/extractor/generic.py | 10 ++++------ youtube_dl/extractor/vimeo.py | 33 ++++++++++++++++++++++++++++++++ 4 files changed, 43 insertions(+), 9 deletions(-) diff --git a/test/test_download.py b/test/test_download.py index 2b8ac6975..8178015ea 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -139,7 +139,9 @@ def try_rm_tcs_files(tcs=None): if is_playlist: self.assertEqual(res_dict['_type'], 'playlist') + self.assertTrue('entries' in res_dict) expect_info_dict(self, test_case.get('info_dict', {}), res_dict) + if 'playlist_mincount' in test_case: assertGreaterEqual( self, @@ -188,7 +190,7 @@ def try_rm_tcs_files(tcs=None): expect_info_dict(self, tc.get('info_dict', {}), info_dict) finally: try_rm_tcs_files() - if is_playlist and res_dict is not None: + if is_playlist and res_dict is not None and res_dict.get('entries'): # Remove all other files that may have been extracted if the # extractor returns full results even with extract_flat res_tcs = [{'info_dict': e} for e in res_dict['entries']] diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6ab3eeaf5..86bff185b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -412,11 +412,12 @@ from .vidme import VidmeIE from .vimeo import ( VimeoIE, - VimeoChannelIE, - VimeoUserIE, VimeoAlbumIE, + VimeoChannelIE, VimeoGroupsIE, + VimeoLikesIE, VimeoReviewIE, + VimeoUserIE, VimeoWatchLaterIE, ) from .vimple import VimpleIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 367f930dd..0dfa4853d 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -397,12 +397,6 @@ class GenericIE(InfoExtractor): }, ] - def report_download_webpage(self, video_id): - """Report webpage download.""" - if not self._downloader.params.get('test', False): - self._downloader.report_warning('Falling back on generic information extractor.') - super(GenericIE, self).report_download_webpage(video_id) - def report_following_redirect(self, new_url): """Report information extraction.""" self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) @@ -502,6 +496,7 @@ def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url) force_videoid = None + is_intentional = smuggled_data and smuggled_data.get('to_generic') if smuggled_data and 'force_videoid' in smuggled_data: force_videoid = smuggled_data['force_videoid'] video_id = force_videoid @@ -544,6 +539,9 @@ def _real_extract(self, url): 'upload_date': upload_date, } + if not self._downloader.params.get('test', False) and not is_intentional: + self._downloader.report_warning('Falling back on generic information extractor.') + try: webpage = self._download_webpage(url, video_id) except ValueError: diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index bc01d7fbf..4be1b8785 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -15,6 +15,7 @@ get_element_by_attribute, ExtractorError, RegexNotFoundError, + smuggle_url, std_headers, unsmuggle_url, urlencode_postdata, @@ -529,3 +530,35 @@ def _page_url(self, base_url, pagenum): def _real_extract(self, url): return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater') + + +class VimeoLikesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P[0-9]+)/likes(?:$|[?#])' + IE_NAME = 'vimeo:likes' + IE_DESC = 'Vimeo user likes' + _TEST = { + 'url': 'https://vimeo.com/user20132939/likes', + 'playlist_mincount': 4, + 'add_ies': ['Generic'], + "info_dict": { + "description": "Videos Philipp Hagemeister likes on Vimeo.", + "title": "Vimeo / Philipp Hagemeister's likes", + }, + 'params': { + 'extract_flat': False, + }, + } + + def _real_extract(self, url): + user_id = self._match_id(url) + rss_url = '%s//vimeo.com/user%s/likes/rss' % ( + self.http_scheme(), user_id) + surl = smuggle_url(rss_url, { + 'force_videoid': '%s_likes' % user_id, + 'to_generic': True, + }) + + return { + '_type': 'url', + 'url': surl, + }