From 691008087b902fa731a8f4f840c1821c93505840 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sat, 31 Aug 2013 15:05:59 +0200 Subject: [PATCH 1/3] Add an automatic page generator for the supported sites (related #156) They are listed in the "supportedsites.html" page. --- devscripts/gh-pages/update-sites.py | 33 +++++++++++++++++++++++++++++ devscripts/release.sh | 1 + 2 files changed, 34 insertions(+) create mode 100755 devscripts/gh-pages/update-sites.py diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py new file mode 100755 index 000000000..fa4bb2beb --- /dev/null +++ b/devscripts/gh-pages/update-sites.py @@ -0,0 +1,33 @@ +#!/usr/bin/env python3 + +import sys +import os +import textwrap + +# We must be able to import youtube_dl +sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) + +import youtube_dl + +def main(): + with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf: + template = tmplf.read() + + ie_htmls = [] + for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME): + ie_html = '{}'.format(ie.IE_NAME) + try: + ie_html += ': {}'.format(ie.IE_DESC) + except AttributeError: + pass + if ie.working() == False: + ie_html += ' (Currently broken)' + ie_htmls.append('
  • {}
  • '.format(ie_html)) + + template = template.replace('@SITES@', textwrap.indent('\n'.join(ie_htmls), '\t')) + + with open('supportedsites.html', 'w', encoding='utf-8') as sitesf: + sitesf.write(template) + +if __name__ == '__main__': + main() diff --git a/devscripts/release.sh b/devscripts/release.sh index 24c9ad8d8..62c68a6cf 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -85,6 +85,7 @@ ROOT=$(pwd) "$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem" "$ROOT/devscripts/gh-pages/generate-download.py" "$ROOT/devscripts/gh-pages/update-copyright.py" + "$ROOT/devscripts/gh-pages/update-sites.py" git add *.html *.html.in update git commit -m "release $version" git show HEAD From 6c758d79de48956b90d9e78aec695ee0b10b00d2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sat, 31 Aug 2013 22:35:39 +0200 Subject: [PATCH 2/3] [metacafe] Add more cases for detecting the uploader detection (reported in #1343) --- youtube_dl/extractor/metacafe.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index e38dc98b4..e537648ff 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -122,7 +122,7 @@ def _real_extract(self, url): video_title = self._html_search_regex(r'(?im)(.*) - Video', webpage, u'title') description = self._og_search_description(webpage) video_uploader = self._html_search_regex( - r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("channel","([^"]+)"\);', + r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', webpage, u'uploader nickname', fatal=False) return { From 8e4e89f1c236e1bec38c5363c1c341930056211e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 2 Sep 2013 11:54:09 +0200 Subject: [PATCH 3/3] Add an extractor for VeeHD (closes #1359) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/veehd.py | 56 ++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/veehd.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 90f1a4418..9f56e427c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -89,6 +89,7 @@ from .unistra import UnistraIE from .ustream import UstreamIE from .vbox7 import Vbox7IE +from .veehd import VeeHDIE from .veoh import VeohIE from .vevo import VevoIE from .videofyme import VideofyMeIE diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py new file mode 100644 index 000000000..3a99a29c6 --- /dev/null +++ b/youtube_dl/extractor/veehd.py @@ -0,0 +1,56 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + get_element_by_id, + clean_html, +) + +class VeeHDIE(InfoExtractor): + _VALID_URL = r'https?://veehd.com/video/(?P\d+)' + + _TEST = { + u'url': u'http://veehd.com/video/4686958', + u'file': u'4686958.mp4', + u'info_dict': { + u'title': u'Time Lapse View from Space ( ISS)', + u'uploader_id': u'spotted', + u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"', + webpage, u'player path') + player_url = compat_urlparse.urljoin(url, player_path) + player_page = self._download_webpage(player_url, video_id, + u'Downloading player page') + config_json = self._search_regex(r'value=\'config=({.+?})\'', + player_page, u'config json') + config = json.loads(config_json) + + video_url = compat_urlparse.unquote(config['clip']['url']) + title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) + uploader_id = self._html_search_regex(r'(.+?)', + webpage, u'uploader') + thumbnail = self._search_regex(r'(.*?)