python requests+lxml+xpath 爬取豆瓣top250电影图片

1.爬取豆瓣电影网页源码。

import requests

url = 'https://movie.douban.com/top250?start='+str(start)+'&filter='
data = requests.get(url)
# print(data.text)

2.分析网页结构，爬取图片src，

https://movie.douban.com/top250?start=0&filter=
https://movie.douban.com/top250?start=25&filter=
......

#start为第几个（电影）开始

url = 'https://movie.douban.com/top250?start='+str(start)+'&filter='
data = requests.get(url)
# print(data.text)
page = etree.HTML(data.text)
imglink = page.xpath('//img/@src')

3.下载图片。

    for i in imglink:
        img = requests.get(i)
        open(path+i.split('/')[-1],'wb').write(img.content)    #i.split('/')[-1] 以src最后一个斜杠之后的字符命名图片。
    print('正在保存……')

4.完整代码。

import requests
from lxml import etree

path = 'F:\\douban\\'
def main(start):
    url = 'https://movie.douban.com/top250?start='+str(start)+'&filter='
    data = requests.get(url)
    # print(data.text)
    page = etree.HTML(data.text)
    imglink = page.xpath('//img/@src')
    for i in imglink:
        img = requests.get(i)
        open(path+i.split('/')[-1],'wb').write(img.content)
    print('正在保存……')

if __name__=='__main__':
        for i in range(10):
         main(start=i*25)

5.爬取结果。