Fix some regexes

This commit is contained in:
Sergey M․ 2017-10-09 23:50:53 +07:00
parent 8992331621
commit 197224b7a4
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
30 changed files with 35 additions and 35 deletions

View file

@ -131,7 +131,7 @@ def _real_extract(self, url):
r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
webpage, 'video url', group='url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]

View file

@ -117,7 +117,7 @@ def _real_extract(self, url):
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'url': re.sub(r'_(\d+p.mov)', r'_h\1', src),
'url': re.sub(r'_(\d+p\.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
'language': version[:2],
@ -179,7 +179,7 @@ def _clean_json(m):
formats = []
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'format': format['type'],

View file

@ -195,7 +195,7 @@ def _real_extract(self, url):
title = self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>',
r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>'],
webpage, 'title')
description = self._html_search_meta(

View file

@ -386,7 +386,7 @@ def _process_media_selector(self, media_selection, programme_id):
m3u8_id=format_id, fatal=False))
if re.search(self._USP_RE, href):
usp_formats = self._extract_m3u8_formats(
re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
re.sub(self._USP_RE, r'/\1\.ism/\1\.m3u8', href),
programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
for f in usp_formats:

View file

@ -235,7 +235,7 @@ def _real_extract(self, url):
# vevo embed
vevo_id = self._search_regex(
r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
r'<link rel="video_src" href="[^"]*?vevo\.com[^"]*?video=(?P<id>[\w]*)',
webpage, 'vevo embed', default=None)
if vevo_id:
return self.url_result('vevo:%s' % vevo_id, 'Vevo')

View file

@ -19,7 +19,7 @@ class DeezerPlaylistIE(InfoExtractor):
'id': '176747451',
'title': 'Best!',
'uploader': 'Anonymous',
'thumbnail': r're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
'thumbnail': r're:^https?://cdn-images\.deezer\.com/images/cover/.*\.jpg$',
},
'playlist_count': 30,
'skip': 'Only available in .de',

View file

@ -27,7 +27,7 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
info_json = self._search_regex(r'jQuery.extend\(Drupal.settings, ({.*?})\);', webpage, 'info')
info_json = self._search_regex(r'jQuery\.extend\(Drupal\.settings, ({.*?})\);', webpage, 'info')
info = json.loads(info_json)
return {

View file

@ -2206,7 +2206,7 @@ def _real_extract(self, url):
# And then there are the jokers who advertise that they use RTA,
# but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18

View file

@ -61,7 +61,7 @@ def unicode_escape(s):
'width': int(width),
'height': int(height),
} for width, height, video_url in re.findall(
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent.com.*?)"', webpage)]
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent\.com.*?)"', webpage)]
self._sort_formats(formats)
return {

View file

@ -173,7 +173,7 @@ def _real_extract(self, url):
class HRTiPlaylistIE(HRTiBaseIE):
_VALID_URL = r'https?://hrti.hrt.hr/#/video/list/category/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?'
_VALID_URL = r'https?://hrti\.hrt\.hr/#/video/list/category/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?'
_TESTS = [{
'url': 'https://hrti.hrt.hr/#/video/list/category/212/ekumena',
'info_dict': {

View file

@ -203,7 +203,7 @@ class PCMagIE(IGNIE):
_VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = 'pcmag'
_EMBED_RE = r'iframe.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content.html?[^"]*url=([^"]+)["&]'
_EMBED_RE = r'iframe\.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content\.html?[^"]*url=([^"]+)["&]'
_TESTS = [{
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',

View file

@ -69,9 +69,9 @@ def _extract_rtmp_video(self, webpage):
}]
def _extract_cookies(self, webpage):
policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
policy = self._search_regex(r'InfoQConstants\.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
signature = self._search_regex(r'InfoQConstants\.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
key_pair_id = self._search_regex(r'InfoQConstants\.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
return 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
policy, signature, key_pair_id)

View file

@ -30,7 +30,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, title)
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
config_url = self._html_search_regex(
r'data-src(?:set-video)?="(/contenu/medias/video.php.*?)"',
r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
webpage, 'config URL')
config_url = 'http://www.jeuxvideo.com' + config_url

View file

@ -338,7 +338,7 @@ def _real_extract(self, url):
info = {
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._search_regex(r'channelLogo.src\s*=\s*"([^"]+)"', webpage, 'thumbnail', None),
'thumbnail': self._search_regex(r'channelLogo\.src\s*=\s*"([^"]+)"', webpage, 'thumbnail', None),
}
video_data = self._download_json(stream_url, content_id)
is_live = video_data.get('isLive')

View file

@ -5,7 +5,7 @@
class MakerTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})'
_VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})'
_TEST = {
'url': 'http://www.maker.tv/video/Fh3QgymL9gsc',
'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',

View file

@ -22,7 +22,7 @@ def _real_extract(self, url):
format_url = self._html_search_regex(
[
r'file\s*:\s*"(https?://[^"]+?/playlist.m3u8)',
r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
r'<a[^>]+href="(rtsp://[^"]+)"'
], webpage, 'format url')
formats = self._extract_wowza_formats(

View file

@ -11,7 +11,7 @@
class MeipaiIE(InfoExtractor):
IE_DESC = '美拍'
_VALID_URL = r'https?://(?:www\.)?meipai.com/media/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?meipai\.com/media/(?P<id>[0-9]+)'
_TESTS = [{
# regular uploaded video
'url': 'http://www.meipai.com/media/531697625',

View file

@ -258,7 +258,7 @@ def _extract_mgid(self, webpage):
if mgid is None or ':' not in mgid:
mgid = self._search_regex(
[r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
[r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
webpage, 'mgid', default=None)
if not mgid:

View file

@ -160,7 +160,7 @@ def _real_extract(self, url):
else:
video_playpath = ''
video_swfobj = self._search_regex(r'swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
video_swfobj = self._search_regex(r'swfobject\.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
video_swfobj = compat_urllib_parse_unquote(video_swfobj)
video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",

View file

@ -111,7 +111,7 @@ def _real_extract(self, url):
release_url = self._search_regex(
r'video_auth_playlist_url\s*=\s*"([^"]+)"',
webpage, 'release url')
theplatform_path = self._search_regex(r'https?://link.theplatform.com/s/([^?]+)', release_url, 'theplatform path')
theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path')
video_id = theplatform_path.split('/')[-1]
query = {
'mbr': 'true',

View file

@ -43,7 +43,7 @@ def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
m_id = re.search(r'var rmcPlayer = new nhn\.rmcnmv\.RMCVideoPlayer\("(.+?)", "(.+?)"',
webpage)
if m_id is None:
error = self._html_search_regex(

View file

@ -469,7 +469,7 @@ class SchoolTVIE(NPODataMidEmbedIE):
class HetKlokhuisIE(NPODataMidEmbedIE):
IE_NAME = 'hetklokhuis'
_VALID_URL = r'https?://(?:www\.)?hetklokhuis.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',

View file

@ -25,7 +25,7 @@ def _real_extract(self, url):
video_url = self._html_search_regex(
r'<param name="src" value="([^"]+)"', webpage, 'video url')
title = self._html_search_regex(
r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>',
r'<title>([^<]+)&nbsp;&nbsp; RUHD\.ru - Видео Высокого качества №1 в России!</title>',
webpage, 'title')
description = self._html_search_regex(
r'(?s)<div id="longdesc">(.+?)<span id="showlink">',

View file

@ -66,7 +66,7 @@ def _real_extract(self, url):
r'(?s)<description>([^<]+)</description>',
coursepage, 'description', fatal=False)
links = orderedSet(re.findall(r'<a href="(VideoPage.php\?[^"]+)">', coursepage))
links = orderedSet(re.findall(r'<a href="(VideoPage\.php\?[^"]+)">', coursepage))
info['entries'] = [self.url_result(
'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
) for l in links]
@ -84,7 +84,7 @@ def _real_extract(self, url):
rootpage = self._download_webpage(rootURL, info['id'],
errnote='Unable to download course info page')
links = orderedSet(re.findall(r'<a href="(CoursePage.php\?[^"]+)">', rootpage))
links = orderedSet(re.findall(r'<a href="(CoursePage\.php\?[^"]+)">', rootpage))
info['entries'] = [self.url_result(
'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
) for l in links]

View file

@ -216,7 +216,7 @@ def str_to_hex(str):
def hex_to_bytes(hex):
return binascii.a2b_hex(hex.encode('ascii'))
relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1)
relative_path = re.match(r'https?://link\.theplatform\.com/s/([^?]+)', url).group(1)
clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path))
checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)

View file

@ -57,10 +57,10 @@ def _real_extract(self, url):
info_dict = self._extract_jwplayer_data(
webpage, video_id, require_title=False)
uploader = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
r': <a href="http://www\.thisav\.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
webpage, 'uploader name', fatal=False)
uploader_id = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
r': <a href="http://www\.thisav\.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
webpage, 'uploader id', fatal=False)
info_dict.update({

View file

@ -174,7 +174,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
iframe_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
webpage, 'video iframe', default=None)
if iframe_url:
return self.url_result(iframe_url)

View file

@ -198,7 +198,7 @@ def _real_extract(self, url):
class ViceArticleIE(InfoExtractor):
IE_NAME = 'vice:article'
_VALID_URL = r'https://www.vice.com/[^/]+/article/(?P<id>[^?#]+)'
_VALID_URL = r'https://www\.vice\.com/[^/]+/article/(?P<id>[^?#]+)'
_TESTS = [{
'url': 'https://www.vice.com/en_us/article/on-set-with-the-woman-making-mormon-porn-in-utah',

View file

@ -26,7 +26,7 @@ def _real_extract(self, url):
webpage_url = 'http://videopremium.tv/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
if re.match(r'^<html><head><script[^>]*>window.location\s*=', webpage):
if re.match(r'^<html><head><script[^>]*>window\.location\s*=', webpage):
# Download again, we need a cookie
webpage = self._download_webpage(
webpage_url, video_id,

View file

@ -1683,7 +1683,7 @@ def extract_view_count(v_info):
video_uploader_id = None
video_uploader_url = None
mobj = re.search(
r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
video_webpage)
if mobj is not None:
video_uploader_id = mobj.group('uploader_id')