From b0807d2dcebb0e2853b91f6c886bb3faaafa0bc8 Mon Sep 17 00:00:00 2001 From: Johnny Sun Date: Sun, 13 Nov 2022 05:41:20 -0500 Subject: [PATCH] [callin] Add new extractor --- youtube_dl/extractor/callin.py | 38 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 39 insertions(+) create mode 100644 youtube_dl/extractor/callin.py diff --git a/youtube_dl/extractor/callin.py b/youtube_dl/extractor/callin.py new file mode 100644 index 000000000..50b089e56 --- /dev/null +++ b/youtube_dl/extractor/callin.py @@ -0,0 +1,38 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class CallinIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yourextractor\.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 diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4d9f37424..972aeb9ad 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -158,6 +158,7 @@ from .businessinsider import BusinessInsiderIE from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE +from .callin import CallinIE from .camdemy import ( CamdemyIE, CamdemyFolderIE