mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-01 00:52:58 +01:00
[radiojavan] Simplify and extract upload date
This commit is contained in:
parent
cce23e43a9
commit
7cf97daf77
@ -1,12 +1,14 @@
|
|||||||
# coding: utf-8
|
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import(
|
from ..utils import(
|
||||||
parse_duration,
|
unified_strdate,
|
||||||
str_to_int
|
str_to_int,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class RadioJavanIE(InfoExtractor):
|
class RadioJavanIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
|
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
@ -16,56 +18,49 @@ class RadioJavanIE(InfoExtractor):
|
|||||||
'id': 'chaartaar-ashoobam',
|
'id': 'chaartaar-ashoobam',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Chaartaar - Ashoobam',
|
'title': 'Chaartaar - Ashoobam',
|
||||||
'description': 'Chaartaar - Ashoobam',
|
|
||||||
'thumbnail': 're:^https?://.*\.jpe?g$',
|
'thumbnail': 're:^https?://.*\.jpe?g$',
|
||||||
|
'upload_date': '20150215',
|
||||||
|
'view_count': int,
|
||||||
|
'like_count': int,
|
||||||
|
'dislike_count': int,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, display_id)
|
|
||||||
urls = list()
|
|
||||||
prefix = 'https://media.rdjavan.com/media/music_video/'
|
|
||||||
|
|
||||||
video_url_480 = self._search_regex(
|
webpage = self._download_webpage(url, video_id)
|
||||||
r'RJ\.video480p = \'([^\']+)\'', webpage, '480 video url', fatal= False)
|
|
||||||
video_url_720 = self._search_regex(
|
|
||||||
r'RJ\.video720p = \'([^\']+)\'', webpage, '720 video url', fatal= False)
|
|
||||||
video_url_1080 = self._search_regex(
|
|
||||||
r'RJ\.video1080p = \'([^\']+)\'', webpage, '1080 video url', fatal= False)
|
|
||||||
|
|
||||||
if video_url_480:
|
formats = [{
|
||||||
urls.append({'url': prefix + video_url_480, 'format': '480p'})
|
'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
|
||||||
if video_url_720:
|
'format_id': '%sp' % height,
|
||||||
urls.append({'url': prefix + video_url_720, 'format': '720p'})
|
'height': height,
|
||||||
if video_url_1080:
|
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
|
||||||
urls.append({'url': prefix + video_url_1080, 'format': '1080p'})
|
|
||||||
|
|
||||||
title = self._og_search_title(webpage)
|
title = self._og_search_title(webpage)
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
thumbnail = self._og_search_thumbnail(webpage)
|
||||||
formats = [{
|
|
||||||
'url': url['url'],
|
|
||||||
'format': url['format']
|
|
||||||
} for url in urls]
|
|
||||||
|
|
||||||
likes = self._search_regex(
|
upload_date = unified_strdate(self._search_regex(
|
||||||
r'<span class="rating">([\d,]+)\s*likes</span>', webpage, 'Likes Count', fatal=False )
|
r'class="date_added">Date added: ([^<]+)<',
|
||||||
likes = likes.replace(',', '')
|
webpage, 'upload date', fatal=False))
|
||||||
dislikes = self._search_regex(
|
|
||||||
r'<span class="rating">([\d,]+)\s*dislikes</span>', webpage, 'Dislikes Count', fatal=False )
|
|
||||||
dislikes = dislikes.replace(',', '')
|
|
||||||
|
|
||||||
plays = self._search_regex(
|
view_count = str_to_int(self._search_regex(
|
||||||
r'views_publish[">\s]*<span[^>]+class="views">Plays: ([\d,]+)</span>', webpage, 'Play Count', fatal=False )
|
r'class="views">Plays: ([\d,]+)',
|
||||||
plays = plays.replace(',', '')
|
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))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'formats': formats,
|
'id': video_id,
|
||||||
'id': display_id,
|
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': title, # no description provided in RadioJavan
|
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'like_count': str_to_int(likes),
|
'upload_date': upload_date,
|
||||||
'dislike_count': str_to_int(dislikes),
|
'view_count': view_count,
|
||||||
'viewCount': str_to_int(plays)
|
'like_count': like_count,
|
||||||
|
'dislike_count': dislike_count,
|
||||||
|
'formats': formats,
|
||||||
}
|
}
|
Loading…
Reference in New Issue
Block a user