模拟ajax请求爬取微博

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/9/26 10:26
# @Author  : Sa.Song
# @Desc    : 抓取崔庆才微博， 模拟ajax请求
# @File    : weiBo.py
# @Software: PyCharm

import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
headers = {
    ‘Accept‘:‘application/json, text/plain, */*‘,
    ‘Referer‘:‘https://m.weibo.cn/u/2830678474‘,
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36‘,
    ‘X-Requested-With‘:‘XMLHttpRequest‘,
}
base_url = ‘https://m.weibo.cn/api/container/getIndex?‘

def get_page(page): #page是分页
    parms = {
        ‘type‘:‘uid‘,
        ‘value‘:‘2830678474‘,
        ‘containerid‘:‘1076032830678474‘,
        ‘page‘:page
    }
    url = base_url + urlencode(parms)
    try:
        response = requests.get(url=url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except Exception as e:
        print(‘报错：‘, e)

def parse_message(json):
    weibo_data = []
    if json:
        items = json.get(‘data‘).get(‘cards‘)
        for item in items:
            item = item.get(‘mblog‘)
            if item == None:
                continue
            else:
                weibo_message = {}
                weibo_message[‘id‘] = item.get(‘id‘)
                weibo_message[‘text‘] = pq(item.get(‘text‘)).text()
                weibo_data.append(weibo_message)
    print(weibo_data)

if __name__ == ‘__main__‘:
    for i in range(100):
        json = get_page(i)
        parse_message(json)

原文地址：https://www.cnblogs.com/ss-py/p/9706722.html