python爬虫（二）

post请求，解析的数据格式如：

{"code":0,"msg":"","count":20409,"data":[{"name":"张三"},{"SEX":"男"},{"age":"20"}]}

具体代码

# -*- coding = utf-8 -*-
# @Time: 2021/1/30
# @File: spiderOwner.py
# @Software: PyCharm

import requests
import json
import xlwt


def main():
    baseurl = "http://www.behomesc.com/owner/listData"
    datalist = []
    for i in range(0,99):
        print("第%d页" % (i + 1))
        # 1.爬取网页
        result = requests.post(baseurl, data={"limit": 10, "page": i+1},
                               cookies={"custom.name": "65235d4a-c208-4364-82ed-505c61df22af"})
        # print(result.text)
        # 2.解析数据
        dictR = json.loads(result.text)     # 转换成字典dict
        datas = dictR.get("data")
        for item in datas:
            data = []
            data.append(item.get("toId"))  # 住户ID
            data.append(item.get("toName"))  # 住户名字
            data.append(item.get("toCardNum"))  # 身份证
            data.append(item.get("toPhone"))  # 电话
            data.append(item.get("toBirthday"))  # 生日
            data.append(item.get("toEthnic"))  # 民族
            data.append(item.get("toPhoto"))  # 照片
            datalist.append(data)
    # print(datalist)
    # 3.保存数据
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)
    sheet = book.add_sheet("住户信息", cell_overwrite_ok=True)
    col = ('住户ID', "住户名字", "身份证", "电话", "生日", "民族", "照片")
    print("开始保存。。。")
    for i in range(0, 7):
        sheet.write(0, i, col[i])
    for i in range(0, len(datalist)-1):
        print("第%d条" % (i + 1))
        data = datalist[i]
        for j in range(0, 7):
            sheet.write(i + 1, j, data[j])
    book.save("住户信息.xls")
    print("爬取完毕。。。")


if __name__ == "__main__":
    main()