depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 19:52:11 +00:00
Code Issues Releases Wiki Activity

a working version

Browse source
This commit is contained in:
sprhawk 2017-12-11 15:56:54 +08:00
parent 29ac31afaf
commit 3281af3464
1 changed files with 25 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
youtube_dl/extractor/weibo.py
View file

@ -5,24 +5,19 @@ from .common import InfoExtractor
from urllib.request import Request from urllib.request import Request
from urllib.parse import urlencode from urllib.parse import urlencode
from urllib import parse
import json import json
import random as rnd import random as rnd
from os import path
class WeiboIE(InfoExtractor): class WeiboIE(InfoExtractor):
_VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
_TEST = { _TEST = {
'url': 'https://weibo.com/6275294458/Fp6RGfbff?from=page_1005056275294458_profile&wvr=6&mod=weibotime&type=comment', 'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': { 'info_dict': {
'id': '42', 'id': 'Fp6RGfbff',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Video title goes here', 'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
'thumbnail': r're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
} }
@ -78,20 +73,34 @@ class WeiboIE(InfoExtractor):
}) })
gencallback_url = "https://passport.weibo.com/visitor/visitor?" + param gencallback_url = "https://passport.weibo.com/visitor/visitor?" + param
webpage,urlh = self._download_webpage_handle(gencallback_url, video_id, note="gen callback") webpage,urlh = self._download_webpage_handle(gencallback_url, video_id, note="gen callback")
print("webpage", webpage)
webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="retry to visit the page") webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="retry to visit the page")
print("webpage", webpage)
# TODO more code goes here, for example ... # TODO more code goes here, for example ...
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
video_sources = self._search_regex(r'video-sources=(.+?)', webpage, 'video_sources') video_sources_text = self._search_regex("video-sources=\\\\\"(.+?)\"", webpage, 'video_sources')
print("video_sources:", video_sources)
video_formats = parse.parse_qs(video_sources_text)
formats = []
supported_resolutions = ['720', '480']
for res in supported_resolutions:
f = video_formats.get(res)
if isinstance(f, list):
if len(f) > 0:
vid_url = f[0]
print("%s:%s" % (res, vid_url))
formats.append({
'url': vid_url
})
self._sort_formats(formats)
uploader = self._og_search_property('nick-name', webpage, 'uploader', default = None)
print(title, uploader)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage), 'uploader': uploader,
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), 'formats': formats
# TODO more properties (see youtube_dl/extractor/common.py) # TODO more properties (see youtube_dl/extractor/common.py)
} }