记一次 爬取LOL全皮肤原画保存到本地的实例

 1 #爬取lol全英雄皮肤
 2 import re
 3 import traceback #  异常跟踪
 4 import requests
 5 from bs4 import BeautifulSoup

 6 #获取html
 7 def get_url(url, hander):
 8     try:
 9         r = requests.get(url, headers=hander, timeout=30)
10         r.raise_for_status()
11         r.encoding = r.apparent_encoding
12         return r.text
13     except:
14         traceback.print_exc() #将异常信息打印出来
15         return ""
16 #解析html
17 def prasing_page(lst,html):
18     try:
19         soup = BeautifulSoup(html, "html.parser")
20         for a in soup.find_all(‘li‘, class_=re.compile(‘boxShadow‘)):
21             tag_a = a(‘a‘)
22             for i in tag_a:
23                 lst.append(i[‘href‘])
24         return lst
25     except:
26         traceback.print_exc()
27         return ""


28 #解析获取到的单个html并筛选和下载
29 def getUrl_prasingpag(lst, hander):
30     hero_img_url = []
31     hero_skin_name = []
32     hero_name = []
33     for u in lst:
34         try:
35             r = requests.get(u, headers=hander, timeout=30)
36             r.raise_for_status()
37             r.encoding = r.apparent_encoding

38 　　　　　　　#二次解析
39             soup = BeautifulSoup(r.text, "html.parser")
40             pag = soup.find_all(‘div‘, class_=re.compile(‘othersPifuBox‘))
41             for m in pag:
42                 tag_img = m(‘img‘)
43                 tag_p = m(‘p‘)
44                 tag_span = m(‘span‘)
45                 for m in tag_p:
46                     hero_skin_name.append(m.string)
47                 for m in tag_img:
48                     hero_img_url.append(m[‘src‘])
49                 for m in tag_span:
50                     hero_name.append(m.string)
51         except:
52             traceback.print_exc()  # 将异常信息打印出来
53             continue
54 　　　　　　
　　　　　　　　#下载到本地

55         for i in range(len(hero_name)):
56             try:
57                 path = ‘O:/lol_hero_jpg/‘ + hero_skin_name[i]+‘--‘ + hero_name[i] + ‘.jpg‘
58                 f = open(path, ‘wb‘)
59                 r = requests.get(hero_img_url[i], stream=True)
60                 f.write(r.content)
61                 print("\r当前进度>>>>>>>>>>>>>>>>>>{:.0f}%>>>>>>>>>>>>>>>>>>".format(i * 100 / len(lst)), end="")
62                 f.close()
63             except:
64                 traceback.print_exc()  # 将异常信息打印出来
65                 continue
66 
67 def main():
68     hander = {"User-Agent":"Mozilla/5.0"}
69     deep = 43 #定义爬取页数
70     list = []
71     for i in range(deep):
72         try:
73             url = "http://********/hero_"+str(1+i)+".shtml"
74             html = get_url(url, hander)
75             prasing_page(list, html)
76             getUrl_prasingpag(list, hander)
77         except:
78             continue
79 
80 main()