[python应用]python简单图片抓取

时间:2023-03-10 02:30:25
[python应用]python简单图片抓取

前言

emmmm

python简单图片抓取

 1 import requests
2 import threading
3 import queue
4 from subprocess import Popen,PIPE
5 from bs4 import BeautifulSoup as bs
6 import urllib
7 import base64
8
9
10 queue=queue.Queue()
11
12 class Jiandan(threading.Thread):
13 def __init__(self,queue):
14 threading.Thread.__init__(self)
15 self._queue=queue
16
17 def run(self):
18 while not self._queue.empty():
19 url=self._queue.get_nowait()
20 self.spider(url)
21
22 def spider(self,url):
23 headers={}
24 r=requests.get(url)
25 #选择lxml解析器
26 soup=bs(r.content,'lxml')
27 #查找html标签name为img的元素获取到它
28 imgs=soup.find_all(name='img',attrs={})
29
30 for img in imgs:
31 if 'onload' in str(img):
32 img=img['org_src']
33 else:
34 img=img['src']
35
36 name=img.split('/')[-1]
37
38 #获取的url没http:所以要加上http协议才能访问下载
39 img="http:"+img
40
41 #存储图片的路径地址
42 lu="C:\\Users\\xhds1\\Desktop\\img\\"+name
43 print(lu)
44 urlretrieve(img,lu) #urlretrieve模块下载图片
45 # print(name)
46
47 def main():
48 sss=""
49 for i in range(137,139):
50 riqi="20200121-%s"%(i)
51
52 #使用了base64模块进行URL编码 这里遇到的问题是编码后就成为了字节流类型
53 #查了资料才得知必须转换成字符串类型才行 纠结了好久
54 strbs=base64.b64encode(riqi.encode(encoding="utf-8")).decode("utf-8")
55
56 queue.put("https://jandan.net/pic/"+strbs+"#comments")
57
58 threads=[]
59 thread_count=5
60
61 for i in range(thread_count):
62 threads.append(Jiandan(queue))
63 for t in threads:
64 t.start()
65 for t in threads:
66 t.join()
67
68 if __name__=='__main__':
69 main()

参考学习:

浅析Python3中的bytes和str类型:https://www.cnblogs.com/chownjy/p/6625299.html

https://www.cnblogs.com/OliverQin/p/8641700.html