单线程爬取豆瓣TOP250，超简单

编辑环境：python3.6，pychrm

用到的第三方库：requests，lxml

代码：

import requests
from lxml import etree

for i in range(0, 251, 25):
    num = i
    # 简单的反爬虫处理，如果没有这个，会爬取不了
    headers = {
       'User-Agent':
       'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
        }
    url = F'https://movie.douban.com/top250?start={num}&filter='
    rps = requests.get(url,headers=headers)
    # 得到网页的返回值
    response = rps.text
    # print(text)
    dom = etree.HTML(response)
    # 这里用xpath解析
    items = dom.xpath('//div[@class="item"]')
    # print(items)
    for item in items:
        # 得到电影名字
        picName = item.xpath('div[@class="info"]/div[@class="hd"]/a/span[@class="title"]/text()')[0]
        # print(picName)
        # 得到图片的url
        imgsurl = item.xpath('div[@class="pic"]/a/img/@src')[0]
        # print(imgsurl)
        img = requests.get(imgsurl).content
        # print(img)
        # 保存进文件
        with open("d:/data/"+picName+".jpg", 'wb') as fileWrite:
            fileWrite.write(img)
        print(picName)