etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[tumblr] Simplify and extract duration

Browse source
This commit is contained in:
Sergey M․ 2015-10-05 21:53:01 +06:00
parent 2a27e66234
commit 140ac73965
1 changed files with 32 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
youtube_dl/extractor/tumblr.py
View file

@ -4,6 +4,7 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none
class TumblrIE(InfoExtractor): class TumblrIE(InfoExtractor):
@ -83,8 +84,6 @@ def _real_extract(self, url):
video_id = m_url.group('id') video_id = m_url.group('id')
blog = m_url.group('blog_name') blog = m_url.group('blog_name')
video_urls = []
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id) webpage, urlh = self._download_webpage_handle(url, video_id)
@ -94,34 +93,38 @@ def _real_extract(self, url):
if iframe_url is None: if iframe_url is None:
return self.url_result(urlh.geturl(), 'Generic') return self.url_result(urlh.geturl(), 'Generic')
iframe = self._download_webpage(iframe_url, video_id, iframe = self._download_webpage(iframe_url, video_id, 'Downloading iframe page')
'Downloading iframe page')
sd_video_url = self._search_regex(r'<source src="([^"]+)"', duration = None
iframe, 'sd video url') sources = []
resolution_id = sd_video_url.split("/")[-1] + 'p'
if len(resolution_id) != 4: sd_url = self._search_regex(
resolution_id = None r'<source[^>]+src=(["\'])(?P<url>.+?)\1', iframe,
video_urls.append({ 'sd video url', default=None, group='url')
if sd_url:
sources.append((sd_url, 'sd'))
options = self._parse_json(
self._search_regex(
r'data-crt-options=(["\'])(?P<options>.+?)\1', iframe,
'hd video url', default='', group='options'),
video_id, fatal=False)
if options:
duration = int_or_none(options.get('duration'))
hd_url = options.get('hdUrl')
if hd_url:
sources.append((hd_url, 'hd'))
formats = [{
'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'format_id': 'sd', 'format_id': format_id,
'url': sd_video_url, 'height': int_or_none(self._search_regex(
'resolution': resolution_id, r'/(\d{3,4})$', video_url, 'height', default=None)),
}) 'quality': quality,
} for quality, (video_url, format_id) in enumerate(sources)]
hd_video_url = self._search_regex(r'hdUrl":"([^"]+)"', iframe, self._sort_formats(formats)
'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,
})
# The only place where you can get a title, it's not complete, # The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos # but searching in other places doesn't work for all videos
@ -131,9 +134,10 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'formats': video_urls,
'ext': 'mp4', 'ext': 'mp4',
'title': video_title, 'title': video_title,
'description': self._og_search_description(webpage, default=None), 'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None), 'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'formats': formats,
} }