1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 14:47:44 +01:00
yt-dlp/yt_dlp/extractor/blogger.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

52 lines
1.9 KiB
Python

import re
from ..utils import (
mimetype2ext,
parse_duration,
parse_qs,
str_or_none,
traverse_obj,
)
from .common import InfoExtractor
class BloggerIE(InfoExtractor):
IE_NAME = 'blogger.com'
_VALID_URL = r'https?://(?:www\.)?blogger\.com/video\.g\?token=(?P<id>.+)'
_VALID_EMBED = r'''<iframe[^>]+src=["']((?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']'''
_TESTS = [{
'url': 'https://www.blogger.com/video.g?token=AD6v5dzEe9hfcARr5Hlq1WTkYy6t-fXH3BBahVhGvVHe5szdEUBEloSEDSTA8-b111089KbfWuBvTN7fnbxMtymsHhXAXwVvyzHH4Qch2cfLQdGxKQrrEuFpC1amSl_9GuLWODjPgw',
'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
'info_dict': {
'id': 'BLOGGER-video-3c740e3a49197e16-796',
'title': 'BLOGGER-video-3c740e3a49197e16-796',
'ext': 'mp4',
'thumbnail': r're:^https?://.*',
'duration': 76.068,
}
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(BloggerIE._VALID_EMBED, webpage)
def _real_extract(self, url):
token_id = self._match_id(url)
webpage = self._download_webpage(url, token_id)
data_json = self._search_regex(r'var\s+VIDEO_CONFIG\s*=\s*(\{.*)', webpage, 'JSON data')
data = self._parse_json(data_json.encode('utf-8').decode('unicode_escape'), token_id)
streams = data['streams']
formats = [{
'ext': mimetype2ext(traverse_obj(parse_qs(stream['play_url']), ('mime', 0))),
'url': stream['play_url'],
'format_id': str_or_none(stream.get('format_id')),
} for stream in streams]
return {
'id': data.get('iframe_id', token_id),
'title': data.get('iframe_id', token_id),
'formats': formats,
'thumbnail': data.get('thumbnail'),
'duration': parse_duration(traverse_obj(parse_qs(streams[0]['play_url']), ('dur', 0))),
}