1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-09 19:54:32 +01:00
youtube-dl/youtube_dl/extractor/yam.py

124 lines
4.1 KiB
Python
Raw Normal View History

2015-02-13 08:14:23 +01:00
# coding: utf-8
from __future__ import unicode_literals
import re
2015-02-13 08:14:23 +01:00
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
float_or_none,
month_by_abbreviation,
ExtractorError,
2015-05-09 11:36:07 +02:00
get_element_by_attribute,
)
2015-02-13 08:14:23 +01:00
class YamIE(InfoExtractor):
2015-07-10 18:53:08 +02:00
IE_DESC = '蕃薯藤yam天空部落'
2016-09-08 13:29:05 +02:00
_VALID_URL = r'https?://mymedia\.yam\.com/m/(?P<id>\d+)'
2015-02-13 08:14:23 +01:00
_TESTS = [{
# An audio hosted on Yam
'url': 'http://mymedia.yam.com/m/2283921',
'md5': 'c011b8e262a52d5473d9c2e3c9963b9c',
'info_dict': {
'id': '2283921',
'ext': 'mp3',
'title': '發現 - 趙薇 京華煙雲主題曲',
2015-05-09 11:36:07 +02:00
'description': '發現 - 趙薇 京華煙雲主題曲',
2015-02-13 08:14:23 +01:00
'uploader_id': 'princekt',
'upload_date': '20080807',
'duration': 313.0,
}
}, {
# An external video hosted on YouTube
'url': 'http://mymedia.yam.com/m/3599430',
'md5': '03127cf10d8f35d120a9e8e52e3b17c6',
2015-02-13 08:14:23 +01:00
'info_dict': {
'id': 'CNpEoQlrIgA',
2015-02-13 08:14:23 +01:00
'ext': 'mp4',
'upload_date': '20150306',
2015-02-13 08:14:23 +01:00
'uploader': '新莊社大瑜伽社',
'description': 'md5:11e2e405311633ace874f2e6226c8b17',
2015-02-13 08:14:23 +01:00
'uploader_id': '2323agoy',
'title': '20090412陽明山二子坪-1',
2015-03-12 16:59:46 +01:00
},
'skip': 'Video does not exist',
}, {
'url': 'http://mymedia.yam.com/m/3598173',
'info_dict': {
'id': '3598173',
'ext': 'mp4',
},
'skip': 'cause Yam system error',
}, {
'url': 'http://mymedia.yam.com/m/3599437',
'info_dict': {
'id': '3599437',
'ext': 'mp4',
},
'skip': 'invalid YouTube URL',
2015-05-09 11:36:07 +02:00
}, {
'url': 'http://mymedia.yam.com/m/2373534',
'md5': '7ff74b91b7a817269d83796f8c5890b1',
'info_dict': {
'id': '2373534',
'ext': 'mp3',
'title': '林俊傑&蔡卓妍-小酒窩',
'description': 'md5:904003395a0fcce6cfb25028ff468420',
'upload_date': '20080928',
'uploader_id': 'onliner2',
}
2015-02-13 08:14:23 +01:00
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
2015-02-13 08:14:23 +01:00
# Check for errors
system_msg = self._html_search_regex(
r'系統訊息(?:<br>|\n|\r)*([^<>]+)<br>', page, 'system message',
default=None)
if system_msg:
raise ExtractorError(system_msg, expected=True)
2015-02-13 08:14:23 +01:00
# Is it hosted externally on YouTube?
youtube_url = self._html_search_regex(
r'<embed src="(http://www.youtube.com/[^"]+)"',
page, 'YouTube url', default=None)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
2015-05-09 11:36:07 +02:00
title = self._html_search_regex(
r'<h1[^>]+class="heading"[^>]*>\s*(.+)\s*</h1>', page, 'title')
2015-02-13 08:14:23 +01:00
api_page = self._download_webpage(
'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
note='Downloading API page')
2015-02-13 08:14:23 +01:00
api_result_obj = compat_urlparse.parse_qs(api_page)
2015-05-09 11:36:07 +02:00
info_table = get_element_by_attribute('class', 'info', page)
uploader_id = self._html_search_regex(
2015-05-09 11:36:07 +02:00
r'<!-- 發表作者 -->[\n ]+<a href="/([a-z0-9]+)"',
info_table, 'uploader id', fatal=False)
mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2})\s+' +
2015-02-13 08:14:23 +01:00
r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
if mobj:
upload_date = '%s%02d%02d' % (
mobj.group('year'),
month_by_abbreviation(mobj.group('mon')),
int(mobj.group('day')))
else:
upload_date = None
duration = float_or_none(api_result_obj['totaltime'][0], scale=1000)
2015-02-13 08:14:23 +01:00
return {
'id': video_id,
2015-02-13 08:14:23 +01:00
'url': api_result_obj['mp3file'][0],
2015-05-09 11:36:07 +02:00
'title': title,
'description': self._html_search_meta('description', page),
'duration': duration,
'uploader_id': uploader_id,
2015-02-13 08:14:23 +01:00
'upload_date': upload_date,
}