1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-08 14:36:57 +01:00
yt-dlp/yt_dlp/extractor/myvideoge.py

82 lines
3.3 KiB
Python
Raw Normal View History

import re
2020-08-08 13:24:02 +02:00
from .common import InfoExtractor
from ..utils import (
MONTH_NAMES,
clean_html,
get_element_by_class,
get_element_by_id,
int_or_none,
js_to_json,
qualities,
unified_strdate,
)
2020-08-08 13:24:02 +02:00
class MyVideoGeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?myvideo\.ge/v/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.myvideo.ge/v/3941048',
'md5': '8c192a7d2b15454ba4f29dc9c9a52ea9',
'info_dict': {
'id': '3941048',
'ext': 'mp4',
'title': 'The best prikol',
'upload_date': '20200611',
2020-08-08 13:24:02 +02:00
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'chixa33',
'description': 'md5:5b067801318e33c2e6eea4ab90b1fdd3',
},
2020-08-08 13:24:02 +02:00
}
_MONTH_NAMES_KA = ['იანვარი', 'თებერვალი', 'მარტი', 'აპრილი', 'მაისი', 'ივნისი', 'ივლისი', 'აგვისტო', 'სექტემბერი', 'ოქტომბერი', 'ნოემბერი', 'დეკემბერი']
_quality = staticmethod(qualities(('SD', 'HD')))
2020-08-08 13:24:02 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = (
self._og_search_title(webpage, default=None)
or clean_html(get_element_by_class('my_video_title', webpage))
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title'))
2020-08-08 13:24:02 +02:00
jwplayer_sources = self._parse_json(
self._search_regex(
r'''(?s)jwplayer\s*\(\s*['"]mvplayer['"]\s*\)\s*\.\s*setup\s*\(.*?\bsources\s*:\s*(\[.*?])\s*[,});]''', webpage, 'jwplayer sources', fatal=False)
or '',
video_id, transform_source=js_to_json, fatal=False)
formats = self._parse_jwplayer_formats(jwplayer_sources or [], video_id)
for f in formats or []:
f['quality'] = self._quality(f['format_id'])
2020-08-08 13:24:02 +02:00
description = (
self._og_search_description(webpage)
or get_element_by_id('long_desc_holder', webpage)
or self._html_search_meta('description', webpage))
2020-08-08 13:24:02 +02:00
uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
2020-08-08 13:24:02 +02:00
upload_date = get_element_by_class('mv_vid_upl_date', webpage)
# as ka locale may not be present roll a local date conversion
upload_date = (unified_strdate(
# translate any ka month to an en one
re.sub('|'.join(self._MONTH_NAMES_KA),
lambda m: MONTH_NAMES['en'][self._MONTH_NAMES_KA.index(m.group(0))],
upload_date, flags=re.I))
if upload_date else None)
2020-08-08 13:24:02 +02:00
return {
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': upload_date,
'view_count': int_or_none(get_element_by_class('mv_vid_views', webpage)),
'like_count': int_or_none(get_element_by_id('likes_count', webpage)),
'dislike_count': int_or_none(get_element_by_id('dislikes_count', webpage)),
2020-08-08 13:24:02 +02:00
}