Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[autohome] Add new extractor #24408

Closed
wants to merge 1 commit into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 45 additions & 0 deletions youtube_dl/extractor/autohome.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor

import random


class AutoHomeIE(InfoExtractor):
_VALID_URL = r'https?:\/\/chejiahao\.autohome\.com\.cn\/info\/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://chejiahao.autohome.com.cn/info/2775092',
'md5': 'addbf30e168433f5538b50f58965fc56',
'info_dict': {
'id': '2775092',
'ext': 'mp4',
'title': '宝马的8AT与马自达的6AT谁好!二手RX-8值得买吗?',
'release_date': '2018-09-25',
'description': '极速拍档第九期:买车还要看公司领导的喜好吗?'
}
}

def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)

# TODO more code goes here, for example ...
title = self._html_search_regex(r'<div class="title ">(.+?)</div>', webpage, 'title')
description = self._html_search_regex(r'<div class="videoText">\s*<span>简介:</span>\s*<p class="text">(.+?)</p>\s*</div>', webpage, 'description')
release_date = self._html_search_regex(r'<div class="articleTag">\s*(?:<span>.+?</span>\s*)(?:<span>.+?</span>\s*)(?:<span>(.+?)</span>\s*)</div>', webpage, 'release_date')
vid = self._html_search_regex(r'vid: "(.+?)"', webpage, 'vid')

def _call_api(self, mid, video_id):
return self._download_json('http://p-vp.autohome.com.cn/api/gpi?mid=%s&ft=mp4&strategy=1&r=%s' % (
mid, random.random()), video_id)
url_dict = _call_api(self, vid, video_id)["result"]["media"]["qualities"]
url = [url["copy"] for url in url_dict if url["value"] == 400][0]

return {
'id': video_id,
'title': title,
'url': url,
'description': description,
'release_date': release_date
}
1 change: 1 addition & 0 deletions youtube_dl/extractor/extractors.py
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,7 @@
from .audimedia import AudiMediaIE
from .audioboom import AudioBoomIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .autohome import AutoHomeIE
from .awaan import (
AWAANIE,
AWAANVideoIE,
Expand Down