1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-02-21 17:39:50 +00:00
youtube-dl/youtube_dl/extractor/piapro.py
Dimitrios Semitsoglou-Tsiapos 977e2988db [piapro] initial support
Closes #5856
2019-09-08 09:43:54 +02:00

58 lines
2.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
import re
from datetime import datetime
from ..utils import get_element_by_class
from .common import InfoExtractor
test_partial = {
'md5': 'fe63bb94879189bd9ff7420d0b187352',
'info_dict': {
'artist': 'mothy_悪さん',
'description': '悪ノ娘のアレンジバージョンです。',
'ext': 'mp3',
'id': 'es7uj48x6bvcbtgy',
'thumbnail': r're:https?://c1\.piapro\.jp/timg/nogoc3x8d4m0j416_20080819185021_0180_1440\.jpg',
'timestamp': 1263600322,
'title': 'velvet mix',
'upload_date': '20100116',
'uploader': 'mothy_悪さん',
'uploader_url': r're:https?://piapro\.jp/mothy',
}
}
class PiaproIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?piapro\.jp/(conten)?t/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [dict({'url': 'http://piapro.jp/t/KToM'}, **test_partial),
dict({'url': 'http://piapro.jp/content/es7uj48x6bvcbtgy'}, **test_partial)]
def _real_extract(self, url):
url_id = self._match_id(url)
webpage = self._download_webpage(url, url_id)
if re.search(r'/content/([0-9a-zA-Z]+)', url):
content_id = url_id
else:
content_id = self._search_regex(r'''contentId\s*:\s*['"]([0-9a-zA-Z]+?)['\"]''', webpage, 'content_id')
create_date = self._search_regex(r'''createDate\s*:\s*['"]([0-9]{14})['"]''', webpage, 'create_date', fatal=False) or \
self._search_regex(r'''["']https?://songle\.jp/songs/piapro\.jp.*([0-9]{14})['"]''', webpage, 'create_date')
cls_userbar_name = get_element_by_class("userbar-name", webpage)
uploader = self._search_regex(r'<a.*?>(.+?)</a>', cls_userbar_name, 'uploader', fatal=False)
return {
'artist': uploader,
'description': get_element_by_class("dtl_cap", webpage),
'id': content_id,
'thumbnail': self._search_regex(r'(https?://c1\.piapro\.jp/timg/.+?_1440\.jpg)', webpage, 'thumbnail', fatal=False),
'timestamp': int(datetime.strptime(create_date, '%Y%m%d%H%M%S').strftime("%s")),
'title': get_element_by_class("works-title", webpage) or self._html_search_regex(r'<title>[^<]*「(.*?)」<', webpage, 'title', fatal=False),
'uploader': uploader,
'uploader_url': self._search_regex(r'<a\s+.*?href="(https?://piapro\.jp/.+?)"', cls_userbar_name, 'uploader_url', fatal=False),
'url': 'http://c1.piapro.jp/amp3/{}_{}_audition.mp3'.format(content_id, create_date)
}