Merge pull request #176 from blackjack4494/mtv_updated_extractor_logic

[Mtv] updated extractor logic & more
This commit is contained in:
Tom-Oliver Heidel 2020-10-09 08:01:31 +02:00 committed by GitHub
commit cfd7f14bb3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 73 additions and 10 deletions

View File

@ -3,6 +3,8 @@
from .mtv import MTVServicesInfoExtractor
from ..utils import unified_strdate
# TODO Remove - Reason: Outdated Site
class BetIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'

View File

@ -2,6 +2,8 @@
from .mtv import MTVIE
# TODO Remove - Reason: Outdated Site
class CMTIE(MTVIE):
IE_NAME = 'cmt.com'
@ -39,7 +41,7 @@ class CMTIE(MTVIE):
'only_matching': True,
}]
def _extract_mgid(self, webpage):
def _extract_mgid(self, webpage, url):
mgid = self._search_regex(
r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
webpage, 'mgid', group='mgid', default=None)
@ -50,5 +52,5 @@ def _extract_mgid(self, webpage):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage)
mgid = self._extract_mgid(webpage, url)
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)

View File

@ -48,7 +48,7 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
mgid = self._extract_mgid(webpage, url, data_zone='t2_lc_promo1')
videos_info = self._get_videos_info(mgid)
return videos_info

View File

@ -7,6 +7,7 @@
from ..compat import (
compat_str,
compat_xpath,
compat_urlparse,
)
from ..utils import (
ExtractorError,
@ -22,6 +23,7 @@
unescapeHTML,
update_url_query,
url_basename,
get_domain,
xpath_text,
)
@ -253,7 +255,42 @@ def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
def _extract_mgid(self, webpage):
def _extract_new_triforce_mgid(self, webpage, url='', video_id=None):
# print(compat_urlparse.urlparse(url).netloc)
if url == '':
return
domain = get_domain(url)
if domain is None:
raise ExtractorError(
'[%s] could not get domain' % self.IE_NAME,
expected=True)
url = url.replace("https://", "http://")
enc_url = compat_urlparse.quote(url, safe='')
_TRIFORCE_V8_TEMPLATE = 'https://%s/feeds/triforce/manifest/v8?url=%s'
triforce_manifest_url = _TRIFORCE_V8_TEMPLATE % (domain, enc_url)
manifest = self._download_json(triforce_manifest_url, video_id, fatal=False)
if manifest:
if manifest.get('manifest').get('type') == 'redirect':
self.to_screen('Found a redirect. Downloading manifest from new location')
new_loc = manifest.get('manifest').get('newLocation')
new_loc = new_loc.replace("https://", "http://")
enc_new_loc = compat_urlparse.quote(new_loc, safe='')
triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc)
manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False)
item_id = try_get(manifest, lambda x: x['manifest']['reporting']['itemId'], compat_str)
if not item_id:
self.to_screen('Found no id!')
return
# 'episode' can be anything. 'content' is used often as well
_MGID_TEMPLATE = 'mgid:arc:episode:%s:%s'
mgid = _MGID_TEMPLATE % (domain, item_id)
return mgid
def _extract_mgid(self, webpage, url, data_zone=None):
try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
# or http://media.mtvnservices.com/{mgid}
@ -276,14 +313,17 @@ def _extract_mgid(self, webpage):
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
mgid = self._extract_new_triforce_mgid(webpage, url)
if not mgid:
mgid = self._extract_triforce_mgid(webpage, data_zone)
return mgid
def _real_extract(self, url):
title = url_basename(url)
webpage = self._download_webpage(url, title)
mgid = self._extract_mgid(webpage)
mgid = self._extract_mgid(webpage, url)
videos_info = self._get_videos_info(mgid)
return videos_info

View File

@ -245,5 +245,5 @@ class NickRuIE(MTVServicesInfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage)
mgid = self._extract_mgid(webpage, url)
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)

View File

@ -20,8 +20,18 @@ class BellatorIE(MTVServicesInfoExtractor):
_FEED_URL = 'http://www.bellator.com/feeds/mrss/'
_GEO_COUNTRIES = ['US']
def _extract_mgid(self, webpage):
return self._extract_triforce_mgid(webpage)
def _extract_mgid(self, webpage, url):
mgid = None
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
if not mgid:
mgid = self._extract_new_triforce_mgid(webpage, url)
return mgid
# TODO Remove - Reason: Outdated Site
class ParamountNetworkIE(MTVServicesInfoExtractor):
@ -43,7 +53,7 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
_FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/'
_GEO_COUNTRIES = ['US']
def _extract_mgid(self, webpage):
def _extract_mgid(self, webpage, url):
root_data = self._parse_json(self._search_regex(
r'window\.__DATA__\s*=\s*({.+})',
webpage, 'data'), None)

View File

@ -3,6 +3,8 @@
from .mtv import MTVServicesInfoExtractor
# TODO Remove - Reason: Outdated Site
class VH1IE(MTVServicesInfoExtractor):
IE_NAME = 'vh1.com'

View File

@ -1984,6 +1984,7 @@ def get_elements_by_attribute(attribute, value, html, escape_value=True):
class HTMLAttributeParser(compat_HTMLParser):
"""Trivial HTML parser to gather the attributes for a single element"""
def __init__(self):
self.attrs = {}
compat_HTMLParser.__init__(self)
@ -2378,6 +2379,7 @@ class GeoRestrictedError(ExtractorError):
This exception may be thrown when a video is not available from your
geographic location due to geographic restrictions imposed by a website.
"""
def __init__(self, msg, countries=None):
super(GeoRestrictedError, self).__init__(msg, expected=True)
self.msg = msg
@ -3558,6 +3560,11 @@ def remove_quotes(s):
return s
def get_domain(url):
domain = re.match(r'(?:https?:\/\/)?(?:www\.)?(?P<domain>[^\n\/]+\.[^\n\/]+)(?:\/(.*))?', url)
return domain.group('domain') if domain else None
def url_basename(url):
path = compat_urlparse.urlparse(url).path
return path.strip('/').split('/')[-1]