Python 爬取妹子图

原创于 2017-04-10 21:04:18 发布 · 252 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#url #python

本文介绍了一款用于爬取简丹网特定页面图片的Python爬虫程序。该程序使用requests库获取网页内容，BeautifulSoup解析HTML，通过正则表达式筛选目标链接，并实现了图片的下载保存功能。

import requests
import re
import time
from bs4 import BeautifulSoup

count = 1
url = 'http://jandan.net/ooxx/page-1#comments'      
url_used = []
url_used.append(url)
list1 = []
headers = { 'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}

while len(url_used):
    r = requests.get(url, headers = headers)
    a = r.text
    soup = BeautifulSoup(a, 'html.parser')
    lq = (soup.find("a", {'href': re.compile("^http://jandan.net/ooxx/page-\d*#comments")}))
    list = soup.findAll("img", {'src': re.compile(".*\.jpg")})
    for i in list:
        list1.append(i['src'])
    url = lq['href']
    print(url)
    url_used.append(url)
    for i in list1:
        try:
            b = requests.get('http:' + i, headers=headers, timeout=2)
            print("正在下载第 %d 张" % count)
            count += 1
            path = re.split('/', i)[-1]
            with open(path, 'wb') as f:
                f.write(b.content)
        except:
            print('error')
            continue
    list1 = []