From 81546c4781225f7a45d4883103945ef6b98f821b Mon Sep 17 00:00:00 2001 From: ryanstep Date: Mon, 9 Dec 2024 16:52:36 -0500 Subject: [PATCH] boiler plate --- youtube_dl/extractor/canalrcn.py | 38 ++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 youtube_dl/extractor/canalrcn.py diff --git a/youtube_dl/extractor/canalrcn.py b/youtube_dl/extractor/canalrcn.py new file mode 100644 index 000000000..7d1247e96 --- /dev/null +++ b/youtube_dl/extractor/canalrcn.py @@ -0,0 +1,38 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class YourExtractorIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?canalrcn\.com/watch/(?P[0-9]+)' + _TEST = { + 'url': 'https://yourextractor.com/watch/42', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': '42', + 'ext': 'mp4', + 'title': 'Video title goes here', + 'thumbnail': r're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # TODO more code goes here, for example ... + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + # TODO more properties (see youtube_dl/extractor/common.py) + } \ No newline at end of file