X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcbc.py;h=fd5ec6033b80513012cf2615fc56e80c7e82cadc;hb=416da574ec0df3388f652e44f7fe71b1e3a4701f;hp=54b4b9be958ae49f0ea4f7d37cadcdf4e2c8b1c7;hpb=64f03e5b4c86f7c7e6d660267d77e02da621a94d;p=youtube-dl diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 54b4b9be9..fd5ec6033 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -1,8 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals +import hashlib import json import re +from xml.sax.saxutils import escape from .common import InfoExtractor from ..compat import ( @@ -17,9 +19,11 @@ from ..utils import ( xpath_element, xpath_with_ns, find_xpath_attr, + orderedSet, parse_duration, parse_iso8601, parse_age_limit, + strip_or_none, int_or_none, ExtractorError, ) @@ -129,15 +133,23 @@ class CBCIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) + title = self._og_search_title(webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', default=None) or self._html_search_regex( + r'