爬虫--煎蛋网随手拍

c961850656

#写于学习Python教程P57之后，未使用正则表达式
##网址:http://jandan.net/ooxx
##代码未考虑非jpg格式图片,已知网站还有gif格式图片，有待改进

1. 
   
2. import urllib.request
   
3. import os
   
4. 
   
5. 
   
6. def open_url(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36')
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def find_imgs(url):
    
14.     html = open_url(url).decode('utf-8')
    
15.     pic_list = []
    
16.     a = html.find('查看原图')
    
17.     while a!=-1:
    
18.         c = a + 4
    
19.         a = a - 127
    
20.         b = html.find('.jpg', a) + 4
    
21.         pic_list.append('https://' + html[a:b])
    
22.         a = html.find('查看原图', c)
    
23.     return pic_list
    
24. 
    
25. def get_next_page(url):
    
26.     html = open_url(url).decode('utf-8')
    
27.     a = html.find('下一页') - 80
    
28.     a = html.find('//', a)
    
29.     b = html.find('comments', a)
    
30.     return 'https:' + html[a:b] + 'comments'
    
31. 
    
32. def sava_imgs(folder, pic_list):
    
33.     for each in pic_list:
    
34.         filename = each.split('/')[-1]
    
35.         with open(filename,'wb') as f:
    
36.             img = open_url(each)
    
37.             f.write(img)
    
38. 
    
39. def g_pic_dl(folder='妹子图',pages=10):
    
40.     pic_list = []
    
41.     url = "http://jandan.net/ooxx"
    
42.     os.mkdir(folder)
    
43.     os.chdir(folder)
    
44.     while pages > 0:
    
45.         pic_list=find_imgs(url)
    
46.         sava_imgs(folder, pic_list)
    
47.         url = get_next_page(url)
    
48. 
    
49. if __name__ == '__main__':
    
50.     g_pic_dl()
    
51. 
    

复制代码

c961850656

#写于学习完Python教程P61之后
小甲鱼对Ip地址的正则表达式有小bug
自己学习理解后写出对Ipv4地址的如下正则

1. 
   
2. r'((25[0-5]|2[0-4][0-9]|1\d\d|\d\d|\d)\.){3}(25[0-5]|2[0-4][0-9]|1\d\d|\d\d|\d)'
   

复制代码

单独一段三位数测试如下：

1. 
   
2. for i in range(1,256):
   
3.         re.search(r'(25[0-5]|2[0-4][0-9]|1\d\d|\d\d|\d)', str(i))
   

复制代码

#加入正则表达式后对随手拍的爬虫代码(正常下载jpg及gif)：

1. 
   
2. import urllib.request
   
3. import os
   
4. import re
   
5. 
   
6. def open_url(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36')
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def find_imgs(url):
    
14.     html = open_url(url).decode('utf-8')
    
15.     p = r'<a href="([^"]+.(?:jpg|gif))"'
    
16.     pic_list = re.findall(p, html)
    
17.     return pic_list
    
18.    
    
19. 
    
20. def get_next_page(url):
    
21.     html = open_url(url).decode('utf-8')
    
22.     p = r'<a title="Older Comments" href="([^"]+)"'
    
23.     _result = re.search(p, html)
    
24.     new_url = 'https:' + _result.group(1)
    
25.     return new_url
    
26. 
    
27. def sava_imgs(pic_list):
    
28.     for each in pic_list:
    
29.         filename = each.split('/')[-1]
    
30.         each = 'https:' + each
    
31.         urllib.request.urlretrieve(each,filename)
    
32. 
    
33. def g_pic_dl(folder='妹子图',pages=5):
    
34.     pic_list = []
    
35.     url = "https://jandan.net/ooxx"
    
36.     if os.path.isdir(folder) == 0:
    
37.         os.mkdir(folder)
    
38.     os.chdir(folder)
    
39.     while pages > 0:
    
40.         pic_list=find_imgs(url)
    
41.         sava_imgs(pic_list)
    
42.         url = get_next_page(url)
    
43.         pages -= 1
    
44. 
    
45. if __name__ == '__main__':
    
46.     g_pic_dl()
    
47. 
    

复制代码

昕颖

1.     raise HTTPError(req.full_url, code, msg, hdrs, fp)
   
2. urllib.error.HTTPError: HTTP Error 403: Forbidden

复制代码

这个没有加入正则表达式的代码  不行    403了   希望可以解决一下