From 27fe903c511691c078942bef5ee9a05a43b15c8f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jes=C3=BAs?= Date: Wed, 9 Jun 2021 17:54:27 -0500 Subject: initial --- hypervideo_dl/extractor/canalc2.py | 73 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 hypervideo_dl/extractor/canalc2.py (limited to 'hypervideo_dl/extractor/canalc2.py') diff --git a/hypervideo_dl/extractor/canalc2.py b/hypervideo_dl/extractor/canalc2.py new file mode 100644 index 0000000..407cc80 --- /dev/null +++ b/hypervideo_dl/extractor/canalc2.py @@ -0,0 +1,73 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class Canalc2IE(InfoExtractor): + IE_NAME = 'canalc2.tv' + _VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P\d+)' + + _TESTS = [{ + 'url': 'http://www.canalc2.tv/video/12163', + 'md5': '060158428b650f896c542dfbb3d6487f', + 'info_dict': { + 'id': '12163', + 'ext': 'mp4', + 'title': 'Terrasses du Numérique', + 'duration': 122, + }, + }, { + 'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'http://www.canalc2.tv/video/%s' % video_id, video_id) + + title = self._html_search_regex( + r'(?s)class="[^"]*col_description[^"]*">.*?

(.+?)

', + webpage, 'title') + + formats = [] + for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage): + if video_url.startswith('rtmp://'): + rtmp = re.search( + r'^(?Prtmp://[^/]+/(?P.+/))(?Pmp4:.+)$', video_url) + formats.append({ + 'url': rtmp.group('url'), + 'format_id': 'rtmp', + 'ext': 'flv', + 'app': rtmp.group('app'), + 'play_path': rtmp.group('play_path'), + 'page_url': url, + }) + else: + formats.append({ + 'url': video_url, + 'format_id': 'http', + }) + + if formats: + info = { + 'formats': formats, + } + else: + info = self._parse_html5_media_entries(url, webpage, url)[0] + + self._sort_formats(info['formats']) + + info.update({ + 'id': video_id, + 'title': title, + 'duration': parse_duration(self._search_regex( + r'id=["\']video_duree["\'][^>]*>([^<]+)', + webpage, 'duration', fatal=False)), + }) + return info -- cgit v1.2.3