yt-dlp/youtube_dlc/extractor/zoomus.py

83 lines
3.4 KiB
Python
Raw Normal View History

2020-04-12 21:27:58 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
2020-04-12 21:27:58 +00:00
int_or_none,
2020-04-13 05:27:56 +00:00
url_or_none,
parse_filesize,
urlencode_postdata
2020-04-12 21:27:58 +00:00
)
class ZoomUSIE(InfoExtractor):
IE_NAME = 'zoom.us'
_VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/play/(?P<id>[A-Za-z0-9\-_]+)'
2020-04-12 21:27:58 +00:00
2020-04-12 22:18:40 +00:00
_TEST = {
2020-04-12 21:27:58 +00:00
'url': 'https://zoom.us/recording/play/SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK',
'info_dict': {
2020-04-12 22:18:40 +00:00
'md5': '031a5b379f1547a8b29c5c4c837dccf2',
'title': "GAZ Transformational Tuesdays W/ Landon & Stapes",
'id': "SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK",
2020-04-13 05:27:56 +00:00
'ext': "mp4"
2020-04-12 21:27:58 +00:00
}
2020-04-12 22:18:40 +00:00
}
2020-04-12 21:27:58 +00:00
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
password_protected = self._search_regex(r'<form[^>]+?id="(password_form)"', webpage, 'password field', fatal=False, default=None)
if password_protected is not None:
self._verify_video_password(url, display_id, webpage)
webpage = self._download_webpage(url, display_id)
2020-04-12 21:27:58 +00:00
video_url = self._search_regex(r"viewMp4Url: \'(.*)\'", webpage, 'video url')
2020-04-13 05:27:56 +00:00
title = self._html_search_regex([r"topic: \"(.*)\",", r"<title>(.*) - Zoom</title>"], webpage, 'title')
viewResolvtionsWidth = self._search_regex(r"viewResolvtionsWidth: (\d*)", webpage, 'res width', fatal=False)
viewResolvtionsHeight = self._search_regex(r"viewResolvtionsHeight: (\d*)", webpage, 'res height', fatal=False)
fileSize = parse_filesize(self._search_regex(r"fileSize: \'(.+)\'", webpage, 'fileSize', fatal=False))
2020-04-12 21:27:58 +00:00
urlprefix = url.split("zoom.us")[0] + "zoom.us/"
2020-04-12 21:27:58 +00:00
formats = []
formats.append({
2020-04-13 05:27:56 +00:00
'url': url_or_none(video_url),
2020-04-12 21:27:58 +00:00
'width': int_or_none(viewResolvtionsWidth),
'height': int_or_none(viewResolvtionsHeight),
2020-04-12 22:18:40 +00:00
'http_headers': {'Accept': 'video/webm,video/ogg,video/*;q=0.9,application/ogg;q=0.7,audio/*;q=0.6,*/*;q=0.5',
'Referer': urlprefix},
2020-04-13 05:27:56 +00:00
'ext': "mp4",
'filesize_approx': int_or_none(fileSize)
2020-04-12 21:27:58 +00:00
})
self._sort_formats(formats)
return {
'id': display_id,
2020-04-13 05:27:56 +00:00
'title': title,
2020-04-12 21:27:58 +00:00
'formats': formats
2020-04-12 22:18:40 +00:00
}
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword')
if password is None:
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
meetId = self._search_regex(r'<input[^>]+?id="meetId" value="([^\"]+)"', webpage, 'meetId')
data = urlencode_postdata({
'id': meetId,
'passwd': password,
'action': "viewdetailedpage",
'recaptcha': ""
})
validation_url = url.split("zoom.us")[0] + "zoom.us/rec/validate_meet_passwd"
validation_response = self._download_json(
validation_url, video_id,
note='Validating Password...',
errnote='Wrong password?',
data=data)
if validation_response['errorCode'] != 0:
raise ExtractorError('Login failed, %s said: %r' % (self.IE_NAME, validation_response['errorMessage']))