From 75c9481224ab435aa8c38403644a0e8b46b76db0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 27 Jun 2013 00:09:51 +0200 Subject: [PATCH] ArteTvIE: rewrite the extract process to support the new site (fixes #875) The video can be downloaded with rtmp or http, but the best quality format seems to always use rtmp. Deleted the old methods. --- youtube_dl/extractor/arte.py | 122 +++++++++++------------------------ 1 file changed, 36 insertions(+), 86 deletions(-) diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 82e3ffe04..b061b9566 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -1,53 +1,21 @@ import re -import socket +import json from .common import InfoExtractor from ..utils import ( - compat_http_client, - compat_str, - compat_urllib_error, + # This is used by the not implemented extractLiveStream method compat_urllib_parse, - compat_urllib_request, ExtractorError, unified_strdate, ) class ArteTvIE(InfoExtractor): - """arte.tv information extractor.""" - - _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' + _VALID_URL = r'(?:http://)?www\.arte.tv/guide/(?:fr|de)/(?:(?:sendungen|emissions)/)?(?P.*?)/(?P.*?)(\?.*)?' _LIVE_URL = r'index-[0-9]+\.html$' IE_NAME = u'arte.tv' - def fetch_webpage(self, url): - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(url) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) - except ValueError as err: - raise ExtractorError(u'Invalid URL: %s' % url) - return webpage - - def grep_webpage(self, url, regex, regexFlags, matchTuples): - page = self.fetch_webpage(url) - mobj = re.search(regex, page, regexFlags) - info = {} - - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - for (i, key, err) in matchTuples: - if mobj.group(i) is None: - raise ExtractorError(err) - else: - info[key] = mobj.group(i) - - return info - # TODO implement Live Stream # def extractLiveStream(self, url): # video_lang = url.split('/')[-4] @@ -75,62 +43,44 @@ class ArteTvIE(InfoExtractor): # ) # video_url = u'%s/%s' % (info.get('url'), info.get('path')) - def extractPlus7Stream(self, url): - video_lang = url.split('/')[-3] - info = self.grep_webpage( - url, - r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', - 0, - [ - (1, 'url', u'Invalid URL: %s' % url) - ] - ) - next_url = compat_urllib_parse.unquote(info.get('url')) - info = self.grep_webpage( - next_url, - r'