爬取明日方舟立绘

Narcissus1

代码写得很烂，看看就行


爬虫基于明日方舟的Wiki：http://prts.wiki/w/%E9%A6%96%E9%A1%B5

1. import requests
   
2. import urllib
   
3. import os
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. pre_url = "http://prts.wiki/w/"
   
7. PATH = os.getcwd()+"\\Arknights\"
   
8. print(PATH)
   
9. 
   
10. def get_res(url):
    
11.     res = requests.get(url)
    
12.     if not res:
    
13.         print(url, "is not a correct url;")
    
14.     return res
    
15. 
    
16. 
    
17. def get_names(html):
    
18.     soup = BeautifulSoup(html.text, 'html.parser')
    
19.     _targets = soup.find_all('div', class_='smwdata')
    
20.     names = []
    
21.     for each in _targets:
    
22.         each = each.get("data-cn")
    
23.         if each:
    
24.             names.append(each.strip())
    
25.     return names
    
26. 
    
27. 
    
28. def get_url(name):
    
29.     url = pre_url + urllib.parse.quote(name)
    
30.     print("正在爬取", name, "的网页，网址为：", url)
    
31.     return url
    
32. 
    
33. 
    
34. def pic_url(url):
    
35.     html = get_res(url)
    
36.     soup = BeautifulSoup(html.text, 'html.parser')
    
37.     images = []
    
38.     for each in soup.find_all('div', id='charimg'):
    
39.         pic1 = each.find('div', id='img-stage1')
    
40.         pic2 = each.find('div', id='img-stage2')
    
41.         if pic1:
    
42.             img1 = pic1.find('img').get('src')
    
43.             images.append(img1)
    
44.         if pic2:
    
45.             img2 = pic2.find('img').get('src')
    
46.             if img2:
    
47.                 images.append(img2)
    
48.     if images:
    
49.         print("成功从网页中找到图片链接!")
    
50.     else:
    
51.         print("ERROR!!!in", url)
    
52.     return images
    
53. 
    
54. 
    
55. def ins_png(urls, name):
    
56.     path = PATH + '立绘\\'
    
57.     if not os.path.exists(path):
    
58.         os.makedirs(path)
    
59.     for i in range(len(urls)):
    
60.         res = requests.get(urls[i])
    
61.         if res:
    
62.             if os.path.exists(path+name+'_'+str(i+1)+'.png'):
    
63.                 return
    
64.             img = open(path+name+'_'+str(i+1)+'.png', 'wb')
    
65.             img.write(res.content)
    
66.             print(name, i+1, "已经保存到", path)
    
67.             img.close()
    
68. 
    
69. 
    
70. def main_code(home_url):
    
71.     html = get_res(home_url)
    
72.     names = get_names(html)
    
73.     for name in names:
    
74.         url = get_url(name)
    
75.         pics = pic_url(url)
    
76.         ins_png(pics, name)
    
77.     print("爬取皮肤函数运行完毕, 请于文件夹中查看\n")
    
78. 
    
79. 
    
80. if __name__ == "__main__":
    
81.     url0 = "http://prts.wiki/w/%E5%B9%B2%E5%91%98%E4%B8%80%E8%A7%88"
    
82.     main_code(url0)

复制代码

良木

瞅瞅