python 爬取数据，并写入数据库

# coding=utf-8

import json
import requests
from bs4 import BeautifulSoup

import db


# 获取data
def get_data(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'};
    response = requests.post(url, headers=headers, verify=False);
    response.encoding = 'utf-8';
    text = response.text;
    # text = text.replace(' ', '');
    # text = text.replace('	', '');
    text = text.replace('\n', '');
    text = text.replace('\r', '');
    return text;


# 数据写入文件
def writeData(listData):
    db.dbInsert(listData)
    # file = open("jd.txt", "a+", encoding='utf-8');
    # for data in listData:
    #     writeData = json.dumps(data, ensure_ascii=False);
    #     file.writelines(writeData);
    #     file.writelines('\n');
    # file.flush();
    # file.close();


# 分析出想要的数据
# 返回的数据格式数list<Object>
def analyzeData(html):
    listData = [];
    soup = BeautifulSoup(html, 'lxml');
    contentList = soup.select('div.p-name');
    for content in contentList:
        detail = {};
        detail['key'] = content.select('a')[0].attrs.get('href');
        detail['value'] = content.text.strip();
        listData.append(detail);
    return listData;


page = 0;
lastKey = '';
while True:
    # 分页获取数据
    page = page + 1;
    url = "";
    data = get_data(url);
    listData = analyzeData(data);
    lastKeyTemp = listData[len(listData) - 1].get('key');
    if lastKeyTemp == lastKey:
        break;
    else:
        lastKey = lastKeyTemp;
    writeData(listData);
# coding=utf-8

import json
import requests
fro