github/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-08-22 22:34:01 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Callin] Add new extractor

Browse source
This commit is contained in:
Ruowang Sun 2022-12-11 11:58:50 -05:00
commit 23dbeb8106
1 changed files with 32 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

43
youtube_dl/extractor/callin.py
View file

@ -2,39 +2,60 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import traverse_obj
class CallinIE(InfoExtractor): class CallinIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?P<id>[^/#?]+)' _VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?:[^/#?-]+-)*(?P<id>[^/#?-]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW', 'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': '2b17390cd9f80fc3cac530883f6e3d6e',
'info_dict': { 'info_dict': {
'id': '42', 'id': 'PrumRdSQJW',
'ext': 'mp4', 'ext': 'mp4',
'title': 'FCC Commissioner Brendan Carr on Elon’s Starlink', 'title': 'FCC Commissioner Brendan Carr on Elon’s Starlink',
'description': 'Or, why the government doesn’t like SpaceX',
} }
}, { }, {
'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA', 'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': 'bd6d6b762e0d5c20cd6090e3d27534a8',
'info_dict': { 'info_dict': {
'id': '42', 'id': 'lzxMidUnjA',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Episode 81- Elites MELT DOWN over Student Debt Victory? Rumble in NYC?', 'title': 'Episode 81- Elites MELT DOWN over Student Debt Victory? Rumble in NYC?',
'description': 'Let’s talk todays episode about the primary election shake up in NYC and the elites melting down over student debt cancelation.',
} }
}] }]
def _search_nextjs_data(self, webpage, video_id, *, transform_source=None, fatal=True, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# webpage_json = self._download_json(url, video_id)
# TODO more code goes here, for example ... next_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['episode']
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title') title = next_data.get('title')
if not title:
title = self._og_search_title(webpage)
description = next_data.get('description')
if not description:
description = self._og_search_description(webpage)
video_url = next_data.get('m3u8')
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4')
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage), 'description': description,
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), 'formats': formats,
# TODO more properties (see youtube_dl/extractor/common.py)
} }