zhihu.py from https://www.zhihu.com/question/37787176

zhihu.py

# -*- coding: utf-8 -*-
# 作者：蓝色
# 链接：https://www.zhihu.com/question/37787176/answer/81607754
# 来源：知乎
# 著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

#! /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('meta itemprop="answerCount" content="(.*?)"',url_content)
# import pdb
# pdb.set_trace()
# print answers
limits = int(answers[0])

while offset < limits:
    post_url = "https://www.zhihu.com/api/v4/questions/37787176/answers"
    params = {
        'sort_by':'default',
        'limit':page_size,
        'offset':offset,
        'include':'data[*].is_normal,admin_closed_comment,reward_info,is_collapsed,annotation_action,annotation_detail,collapse_reason,is_sticky,collapsed_by,suggest_edit,comment_count,can_comment,content,editable_content,voteup_count,reshipment_settings,comment_permission,created_time,updated_time,review_info,question,excerpt,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp,upvoted_followees;data[*].mark_infos[*].url;data[*].author.follower_count,badge[?(type=best_answerer)].topics'
    }
    # 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,
        # authorization 字段从 network->xhr->request-headers 中复制
        'authorization':''
    }
    response = requests.get(post_url, params=params, headers=header)
    # import pdb
    # pdb.set_trace()
    answer_list = response.json()["data"]
    for i in answer_list:
        # print i
        img_urls = re.findall('img .*?src="(?=http)(.*?_hd.*?)"', i['content'])
        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

请问为什么这个程序我跑不了呢？你的post_url我登录上去显示的是错误界面？请问一下是怎么回事呀？answer_list = response.json()["data"]这一行报错KeyError: 'data'

因为需要token

爬出来是IndexError: list index out of range怎么解决呀