python3 简单爬虫

haoabcd2010 2021-12-03 原文

爬取虎牙直播分类页面的主播的头像，名字，人气

今天学习了python3爬虫，上课闲着无聊，自己写了一个爬虫

就顺着老师思路

爬了虎牙直播分类页面的主播，头像，名字，和人气

HuYaCateScrapy.py

 1 #!/usr/bin/python
 2 # -*- coding: utf-8 -*-
 3 
 4 """
 5  @ author:  happy_code
 6  @ contact: happy_code@foxmail.com
 7  @ software: 爬虫
 8  @ desc: 获取虎牙直播类页面主播名和人气,下载头像，并以名字和人气命名
 9 """
10 
11 import urllib
12 import requests
13 import re
14 import os
15 
16 
17 class Spider:
18 
19     # 目标url
20     url = ""
21 
22     # 保存地址
23     myrobot = "D:/scinfo/"
24 
25     # 获取的主播名和人气，头像
26     part = \'<span class="txt">\s*\' \
27         \'\s*<span class="avatar fl">\s*\' \
28             \'\s*<img.*data-original="(.*?)".*>\s*\' \
29             \'\s*<i.*>(.*?)</i>\s*\' \
30         \'\s*</span>\s*\' \
31                 \'\s*<span.*><i.*></i><i class="js-num">(.*?)</i></span>\s*\' \
32     \'\s*</span>\'
33 
34 
35     def __init__(self, url):
36         self.url = url
37 
38 
39     # 获取网站源代码
40     def gethtml(self):
41         res = requests.get(self.url)
42         res.encoding = "UTF-8"
43         return res.text
44 
45 
46     # 获得信息
47     def gethtmlinfo(self):
48         html = self.gethtml()
49         all = re.findall(self.part, html)
50         return all
51 
52 
53     # 下载图片,保存到myrobot下, 可以自定义文件名,哈哈重复下载保证成功(最多3次)
54     def downloadimg(self, url, name=None):
55         ok = 0
56         for i in range(3):
57             try:
58                 if name != None:
59                     path = self.myrobot + name + "." +url.split(\'.\')[-1]
60                 else:
61                     path = self.myrobot + url.split(\'/\')[-1]
62                 url = url.replace(\'\\\', \'\')
63                 r = requests.get(url, timeout=30)
64                 r.raise_for_status()
65                 r.encoding = r.apparent_encoding
66                 if not os.path.exists(self.myrobot):
67                     os.makedirs(self.myrobot)
68                 if not os.path.exists(path):
69                     with open(path, \'wb\') as f:
70                         f.write(r.content)
71                         f.close()
72                         print(path + \' 文件保存成功\')
73                         ok = 1
74                 else:
75                     print(\'文件已经存在\')
76             except:
77                 print("异常")
78                 continue
79 
80             if ok == 1:
81                 break
82 
83     # 保存信息
84     def saveinfo(self, data):
85         for i in data:
86             s.downloadimg(i[0], i[1]+"-"+str(i[2]));
87 
88 
89 if __name__ == "__main__":
90     # lol分类的url
91     s = Spider("https://www.huya.com/g/lol")
92     data = s.gethtmlinfo()
93     s.saveinfo(data)