python豆瓣电影xpath方法索引爬虫并导入数据库

在学了urllib和Fiddler抓包爬虫之后，最大的感触就是费时费力效果也不好，偶然在一篇文章中发现xpath基于开发者工具爬虫并对相同标签进行索引，解决了同一个标题却有多个相同标签的问题，这是写入数据库的效果

爬虫代码
爬虫过程中要注意的问题都在代码中有所注释

import requests
from lxml import etree
import pymysql

def get_url(url):
    url =url
    #防屏蔽代理服务器
    headers ={'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'}
    html =requests.get(url,headers=headers)
    #将html转换为xpath可以匹配
    selector =etree.HTML(html.text)
    #豆瓣电影中有中英文标题，我索引第一个中文标题
    names =selector.xpath('//span[1][@class ="title"]/text()')
    socres =selector.xpath('//span[@class ="rating_num"]/text()')
    ##评价人数span标签没有属性，可以直接索引到第五个span标签
    evluates =selector.xpath('//span[4]/text()')
    summarys =selector.xpath('//span[@class ="inq"]/text()')
    links =selector.xpath('//a[@class =""]/@href')
    # 捕捉异常，防止爬取异常终止
    try:
        for i in range(0,len(evluates)):
            name =names[i]
            socre =socres[i]
            evluate =evluates[i]
            # print(actor[i])
            summary =summarys[i]
            link =links[i]
            # 写进数据库
            conn = pymysql.connect(host='127.0.0.1', user='root', passwd='root', db='dangdang')
            sql = "insert into douban(name,socre,evluate,summary,link) values ('" + name + "','" + socre + "','" + evluate + "','" + summary + "','" + link + "')"
            conn.query(sql)
        conn.close()
    except Exception as e:
        print(e)
#发现网址规律，然后遍历所有网址
for i in range(0,10):
    url ='https://movie.douban.com/top250?start=' + str((i-1)*25) +'&filter='
    get_url(url)


# get_url("https://movie.douban.com/top250?start=0&filter=")