爬虫BeautifulSoup图片下载DEMO

import os, re
import requests
import random
import time
from bs4 import BeautifulSoup

user_agent_list = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
    "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]
UA = random.choice(user_agent_list)  ##从self.user_agent_list中随机取出一个字符串
headers = {'User-Agent': UA}  ##构造成一个完整的User-Agent （UA代表的是上面随机取出来的字符串哦）

url0 = 'http://www.tcu.edu.cn/info/1003/7661.htm'
with requests.get(url0, headers=headers, timeout=5) as response:
    response.encoding=response.apparent_encoding  #确定编码集

    # print('网页全部内容\n',response.text)
    # print('请求返回状态码：  ', response.status_code)
    # print('请求返回头信息：  ', response.headers)
    # print('请求返回cookies：  ', response.cookies)
    # print('请求地址：  ', response.url)
    soup = BeautifulSoup(response.text, 'lxml')

    # print(soup.title.text)  # 打印title

    # print(soup.get_text())  #获取全部文字

    # li_list = soup.find('div', id='vsb_content_2')   #获取正文内容
    # print(li_list.get_text())

    # 提取图片
    img_url_list = soup.find_all('p', class_='vsbcontent_img')

    # print(img_url_list)
    for img_url in img_url_list:
        img_url_a = img_url.find('img')['src']
        print('图片地址:', img_url_a)

        # 补全完整地址
        img_url_a = img_url_a.replace('../..', 'http://www.tcu.edu.cn')
        print('图片地址:', img_url_a)

        img_name = img_url_a.split('/')[-1]  # 取图片名字

        img = requests.get(img_url_a, headers=headers)
        with open('f:\\' + img_name, 'wb') as f1:      #保存图片
            f1.write(img.content)