R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[KeezMovies] Applied requested fixes for PR #16154

Browse Source
This commit is contained in:
Parmjit Virk 2018-04-12 11:07:12 -05:00
parent ecd4c1ddf6
commit c8c6024690
1 changed files with 26 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/keezmovies.py
View File

@ -36,16 +36,22 @@ class KeezMoviesIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_info(self, url): def _get_ids(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = (mobj.group('display_id') display_id = (mobj.group('display_id')
if 'display_id' in mobj.groupdict() if 'display_id' in mobj.groupdict()
else None) or mobj.group('id') else None) or mobj.group('id')
return video_id, display_id
webpage = self._download_webpage( def _download_webpage_age_verified(self, url, display_id):
return self._download_webpage(
url, display_id, headers={'Cookie': 'age_verified=1'}) 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 = [] formats = []
format_urls = set() format_urls = set()
@ -54,7 +60,11 @@ class KeezMoviesIE(InfoExtractor):
duration = None duration = None
encrypted = False encrypted = False
def extract_format(format_url, height=None): 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): if not isinstance(format_url, compat_str):
return return
if format_url in format_urls: if format_url in format_urls:
@ -89,23 +99,22 @@ class KeezMoviesIE(InfoExtractor):
for key, value in flashvars.items(): for key, value in flashvars.items():
mobj = re.search(r'quality_(\d+)[pP]', key) mobj = re.search(r'quality_(\d+)[pP]', key)
if mobj: if mobj:
extract_format(value, int(mobj.group(1))) extract_format(value, int(mobj.group(1)), require_http_prefix=require_http_prefix)
video_url = flashvars.get('video_url') video_url = flashvars.get('video_url')
if video_url and determine_ext(video_url, None): if video_url and determine_ext(video_url, None):
extract_format(video_url) extract_format(video_url, require_http_prefix=require_http_prefix)
video_url = self._html_search_regex( video_url = self._html_search_regex(
r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1', r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
webpage, 'video url', default=None, group='url') webpage, 'video url', default=None, group='url')
if video_url: if video_url:
extract_format(compat_urllib_parse_unquote(video_url)) extract_format(compat_urllib_parse_unquote(video_url), require_http_prefix=require_http_prefix)
if not formats: if not formats:
if 'title="This video is no longer available"' in webpage: if 'title="This video is no longer available"' in webpage:
raise ExtractorError( raise ExtractorError(
'Video %s is no longer available' % video_id, expected=True) 'Video %s is no longer available' % video_id, expected=True)
if len(formats) > 0:
self._sort_formats(formats) self._sort_formats(formats)
if not title: if not title:
@ -123,11 +132,13 @@ class KeezMoviesIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
webpage, info = self._extract_info(url) video_id, display_id = self._get_ids(url)
if len(info['formats']) == 0: webpage = self._download_webpage_age_verified(url, display_id)
embed_url = self._search_regex( embed_url = self._search_regex(
r'<iframe\s+id="embedPlayer"\s+src="//(.+?)"', webpage, 'embed url', fatal=False) r'<iframe\s+id="embedPlayer"\s+src="//(.+?)"', webpage, 'embed url', fatal=False)
return self.url_result(embed_url or url, 'Generic') if embed_url is not None:
return self.url_result(embed_url, 'Generic')
webpage, info = self._extract_info(url, require_http_prefix=False)
info['view_count'] = str_to_int(self._search_regex( info['view_count'] = str_to_int(self._search_regex(
r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False)) r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
return info return info