yt-dlp/youtube_dl/extractor/radiojavan.py

80 lines
2.5 KiB
Python
Raw Normal View History

2015-04-03 18:25:39 +02:00
from __future__ import unicode_literals
import re
2015-04-03 18:25:39 +02:00
from .common import InfoExtractor
from ..utils import (
unified_strdate,
str_to_int,
2018-08-04 15:47:58 +02:00
urlencode_postdata,
2015-04-03 18:25:39 +02:00
)
2015-04-03 18:25:39 +02:00
class RadioJavanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
2018-08-04 15:47:58 +02:00
_HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host'
2015-04-03 18:25:39 +02:00
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
'info_dict': {
'id': 'chaartaar-ashoobam',
'ext': 'mp4',
'title': 'Chaartaar - Ashoobam',
'thumbnail': r're:^https?://.*\.jpe?g$',
'upload_date': '20150215',
'view_count': int,
'like_count': int,
'dislike_count': int,
2015-04-03 18:25:39 +02:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2015-04-03 18:25:39 +02:00
webpage = self._download_webpage(url, video_id)
2015-04-03 18:25:39 +02:00
2018-08-04 15:47:58 +02:00
download_host = self._download_json(
self._HOST_TRACKER_URL,
video_id,
data=urlencode_postdata({'id': video_id}),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': url,
}
)['host']
formats = [{
2018-08-04 15:47:58 +02:00
'url': '%s/%s' % (download_host, video_path),
'format_id': '%sp' % height,
2015-04-04 15:24:37 +02:00
'height': int(height),
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
2015-04-04 15:25:08 +02:00
self._sort_formats(formats)
2015-04-03 18:25:39 +02:00
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'class="date_added">Date added: ([^<]+)<',
webpage, 'upload date', fatal=False))
2015-04-03 18:25:39 +02:00
view_count = str_to_int(self._search_regex(
r'class="views">Plays: ([\d,]+)',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) likes',
webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) dislikes',
webpage, 'dislike count', fatal=False))
2015-04-03 18:25:39 +02:00
return {
'id': video_id,
2015-04-03 18:25:39 +02:00
'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'formats': formats,
}