python爬取百度百科（根据爬取的热词自动匹配相应解释）且将数据存入数据库中

import requests
from lxml import etree
import time, json, requests
import pymysql

header = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36‘,
    ‘cookie‘: ‘BAIDUID=AB4524A16BFAFC491C2D9D7D4CAE56D0:FG=1; BIDUPSID=AB4524A16BFAFC491C2D9D7D4CAE56D0; PSTM=1563684388; MCITY=-253%3A; BDUSS=jZnQkVhbnBIZkNuZXdYd21jMG9VcjdoanlRfmFaTjJ-T1lKVTVYREkxVWp2V2RlSVFBQUFBJCQAAAAAAAAAAAEAAACTSbM~Z3JlYXTL3tGpwOTS9AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACMwQF4jMEBed; pcrightad9384=showed; H_PS_PSSID=1454_21120; delPer=0; PSINO=3; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; __yjsv5_shitong=1.0_7_a3331e3bd00d7cbd253c9e353f581eb2494f_300_1581332649909_58.243.250.219_d03e4deb; yjs_js_security_passport=069e28a2b81f7392e2f39969d08f61c07150cc18_1581332656_js; Hm_lvt_55b574651fcae74b0a9f1cf9c8d7c93a=1580800784,1581160267,1581268654,1581333414; BK_SEARCHLOG=%7B%22key%22%3A%5B%22%E7%96%AB%E6%83%85%22%2C%22%E6%95%B0%E6%8D%AE%22%2C%22%E9%9D%9E%E6%AD%A3%E5%BC%8F%E6%B2%9F%E9%80%9A%22%2C%22mapper%22%5D%7D; Hm_lpvt_55b574651fcae74b0a9f1cf9c8d7c93a=1581334123‘
}
lis=[]
f = open("output.txt", "r", encoding=‘utf-8‘, errors=‘ignore‘)
for line in f:
    info = {}
    line1 = line.split(‘ ‘)[0]
    url = "https://baike.baidu.com/item/" + str(line1)
    info[‘name‘]=line1
    info[‘pinlv‘]=line.split(‘ ‘)[1]
    r = requests.get(url, headers=header)
    html = r.content.decode("utf-8")
    html1 = etree.HTML(html)
    content1 = html1.xpath(‘//div[@class="lemma-summary"]‘)
    if len(content1) == 0:
        content1 = ‘无解释‘
        info[‘content‘] = content1
    else:
        content2 = content1[0].xpath(‘string(.)‘).replace(‘&nbsp‘, ‘‘).replace(‘\n‘, ‘‘)
        info[‘content‘] = content2
    info[‘url‘] = url
    lis.append(info)
print(lis[0])
print(len(lis))
db =  pymysql.connect(host=‘127.0.0.1‘, port=3306, user=‘root‘, password=‘root‘, db=‘reci‘)

cursor = db.cursor()
for i in range(len(lis)):
    cols = ", ".join(‘`{}`‘.format(k) for k in lis[i].keys())
    print(cols)  # ‘`name`, `age`‘

    val_cols = ‘, ‘.join(‘%({})s‘.format(k) for k in lis[i].keys())
    print(val_cols)  # ‘%(name)s, %(age)s‘

    sql = "insert into recifenxi(%s) values(%s)"
    res_sql = sql % (cols, val_cols)
    print(res_sql)  # ‘insert into users(`name`, `age`) values(%(name)s, %(age)s)‘

    cursor.execute(res_sql, lis[i])  # 将字典a传入
    db.commit()