#xpath
#第一种方法 可在开发者工具中找到标签，右键copy xpath，有时需去掉tbody标签
#第二种方法 简单学习xpath，自己书写，掌握基本语法即可，简单的层级关系
#先将csv文件以记事本打开，更改编码为ASNI，保存，再用excel打开即可
import urllib.request
import urllib.parse
import csv
from lxml import etree
#需要cmd pip install lxmlheaders = ['电影名字', '评论', '评分', '名句']
with open('C:\\Users\\lenovo\\Desktop\\mmm.csv','a+',newline='', encoding='utf-8') as f:writer = csv.writer(f)writer.writerow(headers)#先将表头插入
for i in range(10):url ='https://movie.douban.com/top250?start={}&filter='.format(i*25)#发现规律，网址的变化，用format更便捷
response = urllib.request.urlopen(url).read().decode()#源代码html = etree.HTML(response)#建议学习Xpath，非常有用，web自动化中也会用到
name = html.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[1]/a/span[1]/text()')#电影名字comments = html.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[2]/div/span[4]/text()')#电影评价数star = html.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[2]/div/span[2]/text()')#评分quote = html.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[2]/p[2]/span/text()')#名句
with open('C:\\Users\\lenovo\\Desktop\\mmm.csv','a+',newline='', encoding='utf-8') as f:#将数据写入csv文件，a+代表继续写入writer = csv.writer(f)#将文件对象转化成csv对象listw = []for i in range(25):listw = [name[i], comments[i], star[i], quote[i]]writer.writerow(listw)#csv按行写入，写一个列表
