From 2ecbd2ad6fa8bb2d623b8c15e7aaa000a0feb28a Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sat, 15 Oct 2016 00:01:46 +0800 Subject: [PATCH] [chirbit:profile] Fix extraction --- ChangeLog | 1 + youtube_dl/extractor/chirbit.py | 13 +++++-------- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/ChangeLog b/ChangeLog index 29cfe637e..8cc5b93e6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,7 @@ version Extractors +* [chirbit] Fix extraction of user profile pages * [charambatv] Fix extraction * [canalplus] Fix extraction for some videos * [cbsinteractive] Fix extraction for cnet.com diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py index 61aed0167..f35df143a 100644 --- a/youtube_dl/extractor/chirbit.py +++ b/youtube_dl/extractor/chirbit.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import base64 +import re from .common import InfoExtractor from ..utils import parse_duration @@ -70,7 +71,6 @@ class ChirbitProfileIE(InfoExtractor): 'url': 'http://chirbit.com/ScarletBeauty', 'info_dict': { 'id': 'ScarletBeauty', - 'title': 'Chirbits by ScarletBeauty', }, 'playlist_mincount': 3, } @@ -78,13 +78,10 @@ class ChirbitProfileIE(InfoExtractor): def _real_extract(self, url): profile_id = self._match_id(url) - rss = self._download_xml( - 'http://chirbit.com/rss/%s' % profile_id, profile_id) + webpage = self._download_webpage(url, profile_id) entries = [ - self.url_result(audio_url.text, 'Chirbit') - for audio_url in rss.findall('./channel/item/link')] + self.url_result(self._proto_relative_url('//chirb.it/' + video_id)) + for _, video_id in re.findall(r']+id=([\'"])copy-btn-(?P[0-9a-zA-Z]+)\1', webpage)] - title = rss.find('./channel/title').text - - return self.playlist_result(entries, profile_id, title) + return self.playlist_result(entries, profile_id)