From d5822b96b00fce48e04a14953c4cb25cef1cdbaf Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:24:07 +0200 Subject: [PATCH] Move ARD, Arte, ZDF into their own files --- youtube_dl/InfoExtractors.py | 220 +---------------------------------- youtube_dl/extractor/ard.py | 45 +++++++ youtube_dl/extractor/arte.py | 134 +++++++++++++++++++++ youtube_dl/extractor/zdf.py | 65 +++++++++++ 4 files changed, 248 insertions(+), 216 deletions(-) create mode 100644 youtube_dl/extractor/ard.py create mode 100644 youtube_dl/extractor/arte.py create mode 100644 youtube_dl/extractor/zdf.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index f06a8e0c9..e8940ac36 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -21,9 +21,10 @@ import urllib from .utils import * - - from .extractor.common import InfoExtractor, SearchInfoExtractor + +from .extractor.ard import ARDIE +from .extractor.arte import ArteTvIE from .extractor.dailymotion import DailymotionIE from .extractor.metacafe import MetacafeIE from .extractor.statigram import StatigramIE @@ -31,6 +32,7 @@ from .extractor.vimeo import VimeoIE from .extractor.yahoo import YahooIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, YoutubeChannelIE +from .extractor.zdf import ZDFIE @@ -40,125 +42,6 @@ -class ArteTvIE(InfoExtractor): - """arte.tv information extractor.""" - - _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' - _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 - - def extractLiveStream(self, url): - video_lang = url.split('/')[-4] - info = self.grep_webpage( - url, - r'src="(.*?/videothek_js.*?\.js)', - 0, - [ - (1, 'url', u'Invalid URL: %s' % url) - ] - ) - http_host = url.split('/')[2] - next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) - info = self.grep_webpage( - next_url, - r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + - '(http://.*?\.swf).*?' + - '(rtmp://.*?)\'', - re.DOTALL, - [ - (1, 'path', u'could not extract video path: %s' % url), - (2, 'player', u'could not extract video player: %s' % url), - (3, 'url', u'could not extract video url: %s' % url) - ] - ) - 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'