From d8e7e9aa0a4e47ef8171ac755bb4c40e340bec66 Mon Sep 17 00:00:00 2001 From: Parmjit Virk Date: Tue, 17 Apr 2018 12:52:49 -0500 Subject: [PATCH] [KeezMovies] Applied second requested fixes for PR #16154 --- youtube_dl/extractor/common.py | 9 +++++-- youtube_dl/extractor/keezmovies.py | 40 +++++++++++------------------- 2 files changed, 21 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 59b9d3739..0a3776a43 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1078,9 +1078,14 @@ class InfoExtractor(object): html, '%s form' % form_id, group='form') return self._hidden_inputs(form) - def _sort_formats(self, formats, field_preference=None): + def _sort_formats(self, formats, field_preference=None, fatal=True): if not formats: - raise ExtractorError('No video formats found') + msg = 'No video formats found' + if fatal: + raise ExtractorError(msg) + else: + self._downloader.report_warning(msg) + return None for f in formats: # Automatically determine tbr when missing based on abr and vbr (improves diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 1567fe956..a8b4ddcfb 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -36,22 +36,16 @@ class KeezMoviesIE(InfoExtractor): 'only_matching': True, }] - def _get_ids(self, url): + def _extract_info(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') display_id = (mobj.group('display_id') if 'display_id' in mobj.groupdict() else None) or mobj.group('id') - return video_id, display_id - def _download_webpage_age_verified(self, url, display_id): - return self._download_webpage( + webpage = self._download_webpage( url, display_id, headers={'Cookie': 'age_verified=1'}) - def _extract_info(self, url, require_http_prefix=True): - video_id, display_id = self._get_ids(url) - webpage = self._download_webpage_age_verified(url, display_id) - formats = [] format_urls = set() @@ -60,13 +54,9 @@ class KeezMoviesIE(InfoExtractor): duration = None encrypted = False - def extract_format(format_url, height=None, require_http_prefix=True): - if require_http_prefix: - if not isinstance(format_url, compat_str) or not format_url.startswith('http'): - return - else: - if not isinstance(format_url, compat_str): - return + def extract_format(format_url, height=None): + if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//')): + return if format_url in format_urls: return format_urls.add(format_url) @@ -99,23 +89,23 @@ class KeezMoviesIE(InfoExtractor): for key, value in flashvars.items(): mobj = re.search(r'quality_(\d+)[pP]', key) if mobj: - extract_format(value, int(mobj.group(1)), require_http_prefix=require_http_prefix) + extract_format(value, int(mobj.group(1))) video_url = flashvars.get('video_url') if video_url and determine_ext(video_url, None): - extract_format(video_url, require_http_prefix=require_http_prefix) + extract_format(video_url) video_url = self._html_search_regex( r'flashvars\.video_url\s*=\s*(["\'])(?Phttp.+?)\1', webpage, 'video url', default=None, group='url') if video_url: - extract_format(compat_urllib_parse_unquote(video_url), require_http_prefix=require_http_prefix) + extract_format(compat_urllib_parse_unquote(video_url)) if not formats: if 'title="This video is no longer available"' in webpage: raise ExtractorError( 'Video %s is no longer available' % video_id, expected=True) - self._sort_formats(formats) + self._sort_formats(formats, fatal=False) if not title: title = self._html_search_regex( @@ -132,13 +122,11 @@ class KeezMoviesIE(InfoExtractor): } def _real_extract(self, url): - video_id, display_id = self._get_ids(url) - webpage = self._download_webpage_age_verified(url, display_id) - embed_url = self._search_regex( - r'([\d,.]+) Views?', webpage, 'view count', fatal=False)) return info