From 49f5f315fd4640d20107e02195a91108a8223449 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 22:22:08 +0200 Subject: [PATCH] [Spiegel] move into own file --- youtube_dl/InfoExtractors.py | 32 +--------------------------- youtube_dl/extractor/spiegel.py | 37 +++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 31 deletions(-) create mode 100644 youtube_dl/extractor/spiegel.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index c3d0e6191..983010234 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -47,6 +47,7 @@ from .extractor.photobucket import PhotobucketIE from .extractor.pornotube import PornotubeIE from .extractor.rbmaradio import RBMARadioIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE +from .extractor.spiegel import SpiegelIE from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.steam import SteamIE from .extractor.ted import TEDIE @@ -90,37 +91,6 @@ from .extractor.zdf import ZDFIE -class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?(?:#.*)?$' - - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') - - webpage = self._download_webpage(url, video_id) - - video_title = self._html_search_regex(r'
(.*?)
', - webpage, u'title') - - xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' - xml_code = self._download_webpage(xml_url, video_id, - note=u'Downloading XML', errnote=u'Failed to download XML') - - idoc = xml.etree.ElementTree.fromstring(xml_code) - last_type = idoc[-1] - filename = last_type.findall('./filename')[0].text - duration = float(last_type.findall('./duration')[0].text) - - video_url = 'http://video2.spiegel.de/flash/' + filename - video_ext = filename.rpartition('.')[2] - info = { - 'id': video_id, - 'url': video_url, - 'ext': video_ext, - 'title': video_title, - 'duration': duration, - } - return [info] class LiveLeakIE(InfoExtractor): diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py new file mode 100644 index 000000000..98a65b78b --- /dev/null +++ b/youtube_dl/extractor/spiegel.py @@ -0,0 +1,37 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor + + +class SpiegelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?(?:#.*)?$' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'
(.*?)
', + webpage, u'title') + + xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' + xml_code = self._download_webpage(xml_url, video_id, + note=u'Downloading XML', errnote=u'Failed to download XML') + + idoc = xml.etree.ElementTree.fromstring(xml_code) + last_type = idoc[-1] + filename = last_type.findall('./filename')[0].text + duration = float(last_type.findall('./duration')[0].text) + + video_url = 'http://video2.spiegel.de/flash/' + filename + video_ext = filename.rpartition('.')[2] + info = { + 'id': video_id, + 'url': video_url, + 'ext': video_ext, + 'title': video_title, + 'duration': duration, + } + return [info]