X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcbc.py;h=fd5ec6033b80513012cf2615fc56e80c7e82cadc;hb=2391941f283a1107b01f9df76a8b0e521a5abe3b;hp=9faf4022758c46e8ebbd38db74881ad26e692f19;hpb=a88d461dff67205fcec684426afbcbeb4b0e7cf5;p=youtube-dl diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 9faf40227..fd5ec6033 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -1,10 +1,16 @@ # 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 compat_str +from ..compat import ( + compat_str, + compat_HTTPError, +) from ..utils import ( js_to_json, smuggle_url, @@ -13,8 +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, ) @@ -124,15 +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'