|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
本帖最后由 ZedRover 于 2017-6-24 20:04 编辑
#! /usr/bin/env python from urlparse import urlsplit from os.path import basename import urllib2 import re import requests import os import json url = 'https://www.zhihu.com/question/37787176' if not os.path.exists('images'): os.mkdir("images") page_size = 50 offset = 0 url_content = urllib2.urlopen(url).read() answers = re.findall('h3 data-num="(.*?)"', url_content) limits = int(answers[0]) while offset < limits: post_url = "http://www.zhihu.com/node/QuestionAnswerListV2" params = json.dumps({ 'url_token': 37787176, 'pagesize': page_size, 'offset': offset }) data = { '_xsrf': '', 'method': 'next', 'params': params } header = { 'User-Agent': "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:34.0) Gecko/20100101 Firefox/34.0", 'Host': "www.zhihu.com", 'Referer': url } response = requests.post(post_url, data=data, headers=header) answer_list = response.json()["msg"] img_urls = re.findall('img .*?src="(.*?_b.*?)"', ''.join(answer_list)) for img_url in img_urls: try: img_data = urllib2.urlopen(img_url).read() file_name = basename(urlsplit(img_url)[2]) output = open('images/' + file_name, 'wb') output.write(img_data) output.close() except: pass offset += page_size
全文链接
当一个颜值很高的程序员是怎样一番体验?
https://www.zhihu.com/question/37787176?utm_source=com.google.android.apps.docs&utm_medium=social |
|