Python爬虫-爬取网站图片

今天要爬的网站就是

http://www.4j4j.cn/beauty/index.html

进入网站，点开美女图片栏目，打开开发者工具找到我们需要的url，跳转到详情页的url
接下来我们随便点进一个里面，比如第二个美女，进去可以看到她的更多

image.png

可以看到我们想要的图片url，我们只要取到url，然后requests.get(url)就可以把图片下载下来将图片保存到我们的磁盘里

            with open('girl_%d.jpg' % i, 'wb') as fp:
                fp.write(res.content)

这个爬虫也很简单，就不多说了，主要用requests和BeautifulSoup
最后附上完整代码

#!/usr/bin/env python3
# -*- coding:utf-8 -*-

import requests
import os
from bs4 import BeautifulSoup

base_url = 'http://www.4j4j.cn'
index_url = 'http://www.4j4j.cn/beauty/index.html'

# 获取每个美女详情页的url
def get_url_list():
    response = requests.get(index_url)
    response.encoding = 'utf-8'
    html = BeautifulSoup(response.text, 'html.parser')
    data = html.find('div', {'class': 'beautiful_pictures_show'}).find_all('span')
    result = [(item.find('a')['href'], item.find('a').get_text()) for item in data]
    return result

# 下载图片保存到本地
def get_img(beauty_url, title):
    save_path = '/Users/mocokoo/Documents/py_file/%s' % title
    os.mkdir(save_path)
    os.chdir(save_path)
    response = requests.get(beauty_url)
    response.encoding = 'utf-8'
    html = BeautifulSoup(response.text, 'html.parser')
    data = html.find('div', {'class': 'beauty_details_imgs_box'})
    girls = data.find_all('img')
    i = 1
    for girl in girls:
        girl_url = girl['src']
        res = requests.get(girl_url)
        res.encoding = 'utf-8'
        if res.status_code == 200:
            with open('girl_%d.jpg' % i, 'wb') as fp:
                fp.write(res.content)
                i += 1


def get_page():
    url_list = get_url_list()
    for url in url_list:
        beauty_url = base_url+url[0]
        title = url[1]
        get_img(beauty_url=beauty_url, title=title)

if __name__ == '__main__':
    get_page()