yt-dlp/youtube_dl/extractor/tumblr.py

140 lines
5.1 KiB
Python
Raw Normal View History

2014-06-29 07:32:53 +00:00
# -*- coding: utf-8 -*-
2014-01-27 06:36:18 +00:00
from __future__ import unicode_literals
2013-06-23 20:24:07 +00:00
import re
from .common import InfoExtractor
class TumblrIE(InfoExtractor):
2014-09-14 10:20:14 +00:00
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
2014-06-29 07:08:46 +00:00
_TESTS = [{
2014-01-27 06:36:18 +00:00
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767',
'info_dict': {
2014-06-29 07:08:46 +00:00
'id': '54196191430',
'ext': 'mp4',
'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
2014-10-25 20:42:56 +00:00
'description': 'md5:37db8211e40b50c7c44e95da14f630b7',
2014-06-29 07:08:46 +00:00
'thumbnail': 're:http://.*\.jpg',
2013-06-27 18:46:46 +00:00
}
2014-06-29 07:08:46 +00:00
}, {
'url': 'http://5sostrum.tumblr.com/post/90208453769/yall-forgetting-the-greatest-keek-of-them-all',
'md5': 'bf348ef8c0ef84fbf1cbd6fa6e000359',
'info_dict': {
'id': '90208453769',
'ext': 'mp4',
2014-10-25 20:42:56 +00:00
'title': '5SOS STRUM ;]',
2014-06-29 07:08:46 +00:00
'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg',
}
}, {
'url': 'http://hdvideotest.tumblr.com/post/130323439814/test-description-for-my-hd-video',
'md5': '99a84522f60972bf064a0b80f87bcbb5',
'info_dict': {
'id': '130323439814',
'ext': 'mp4',
'title': 'HD Video Testing \u2014 Test description for my HD video',
'description': 'md5:97cc3ab5fcd27ee4af6356701541319c',
'thumbnail': 're:http://.*\.jpg',
},
'params': {
'format': 'sd',
},
}, {
'url': 'http://hdvideotest.tumblr.com/post/130323439814/test-description-for-my-hd-video',
'md5': '7ae503065ad150122dc3089f8cf1546c',
'info_dict': {
'id': '130323439814',
'ext': 'mp4',
'title': 'HD Video Testing \u2014 Test description for my HD video',
'description': 'md5:97cc3ab5fcd27ee4af6356701541319c',
'thumbnail': 're:http://.*\.jpg',
},
'params': {
'format': 'hd',
},
}, {
'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
'info_dict': {
'id': 'Wmur',
'ext': 'mp4',
'title': 'naked smoking & stretching',
'upload_date': '20150506',
'timestamp': 1430931613,
},
'add_ie': ['Vidme'],
}, {
'url': 'http://camdamage.tumblr.com/post/98846056295/',
'md5': 'a9e0c8371ea1ca306d6554e3fecf50b6',
'info_dict': {
'id': '105463834',
'ext': 'mp4',
'title': 'Cam Damage-HD 720p',
'uploader': 'John Moyer',
'uploader_id': 'user32021558',
},
'add_ie': ['Vimeo'],
2014-06-29 07:08:46 +00:00
}]
2013-06-23 20:24:07 +00:00
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
video_id = m_url.group('id')
blog = m_url.group('blog_name')
video_urls = []
2013-06-23 20:24:07 +00:00
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id)
2014-10-25 20:42:56 +00:00
iframe_url = self._search_regex(
r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
webpage, 'iframe url', default=None)
if iframe_url is None:
return self.url_result(urlh.geturl(), 'Generic')
2015-07-20 10:54:47 +00:00
iframe = self._download_webpage(iframe_url, video_id,
'Downloading iframe page')
sd_video_url = self._search_regex(r'<source src="([^"]+)"',
iframe, 'sd video url')
resolution_id = sd_video_url.split("/")[-1] + 'p'
if len(resolution_id) != 4:
resolution_id = None
video_urls.append({
'ext': 'mp4',
'format_id': 'sd',
'url': sd_video_url,
'resolution': resolution_id,
})
hd_video_url = self._search_regex(r'hdUrl":"([^"]+)"', iframe,
'hd video url', default=None)
if hd_video_url:
hd_video_url = hd_video_url.replace("\\", "")
resolution_id = hd_video_url.split("/")[-1] + 'p'
if len(resolution_id) != 4:
resolution_id = None
video_urls.append({
'ext': 'mp4',
'format_id': 'hd',
'url': hd_video_url,
'resolution': resolution_id,
})
2013-06-23 20:24:07 +00:00
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
2014-09-14 10:20:14 +00:00
video_title = self._html_search_regex(
r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, 'title')
2013-06-23 20:24:07 +00:00
2014-09-14 10:20:14 +00:00
return {
'id': video_id,
'formats': video_urls,
2014-10-25 20:42:56 +00:00
'ext': 'mp4',
'title': video_title,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
2014-09-14 10:20:14 +00:00
}