python爬虫-爬取你想要的小姐姐

一、准备

1. 原地址

2. 检查html发现，网页是有规则的分页, 最大图片的class为pic-large

 

二、代码

 1 import requests
 2 import os
 3 from bs4 import BeautifulSoup
 4 
 5 url = 'http://www.win4000.com/wallpaper_detail_157712.html'
 6 imgmkdir = 'D://Download//ghost_1//'
 7 
 8 
 9 # 获取网页url
10 def getUrlList():
11     imgUrlList = []
12     for i in range(0, 10):
13         imgUrl = ''
14         url_split = url.split('.html')
15         if not i == 0:
16             imgUrl += url_split[0] + '_' + str(i) + '.html'
17             # print(imgUrl)
18             imgUrlList.append(imgUrl)
19 
20     return imgUrlList
21 
22 
23 # 下载图片
24 def downImg(imgUrl):
25     try:
26         if not os.path.exists(imgmkdir):
27             os.mkdir(imgmkdir)
28         if not os.path.exists(imgUrl):
29             r = requests.get(imgUrl)
30             r.raise_for_status()
31             # 使用with语句可以不用自己手动关闭已经打开的文件流
32             imgpath = imgmkdir + imgUrl.split('/')[-1]
33             # 开始写文件, wb表示写二进制文件
34             with open(imgpath, 'wb') as f:
35                 f.write(r.content)
36             print(imgUrl + '【爬取完成】')
37         else:
38             print(imgUrl.split('/')[-1] + '【文件已存在】')
39     except Exception as e:
40         print("爬取失败" + str(e))
41 
42 
43 # 获取imgHtml标签
44 def getcontent(soup):
45     for i in soup.find_all('img', class_='pic-large'):
46         imgsrc = i['src']
47         if imgsrc.find('http') >= 0 or imgsrc.find('https') >= 0:
48             # 下载图片
49             downImg(imgsrc)
50 
51 
52 # 根据url获取html源码
53 def getHtmlByUrl(htmlUrl):
54     htmlText = requests.get(htmlUrl).content
55     # 使用beautifulSoup解析html
56     soup = BeautifulSoup(htmlText, 'lxml')
57 
58     return soup
59 
60 
61 def main():
62     htmlUrlList = getUrlList()
63     for url in htmlUrlList:
64         htmltext = getHtmlByUrl(url)
65         getcontent(htmltext)
66 
67 
68 if __name__ == '__main__':
69     main()

三、结果

四、总结

　　代码用比较笨的方法来获取，先试水