今天研究写了个简单的图片爬虫

代码：

 1 import requests
 2 import urllib
 3 
 4 def callFunc():
 5     url = "http://lab.scrapyd.cn/archives/55.html"
 6     content = requests.get(url, timeout=None)
 7     content1 = content.text
 8     #print(content1)
 9 
10     head = '''<img src="'''
11     tail ='''.jpg"'''
12 
13     i =0
14     
15     while i < 10:
16         positionBegin = content1.find(head)
17         positionEnd   = content1.find(tail, positionBegin)
18 
19         picUrl = content1[positionBegin + len(head) : positionEnd+len(tail)-1]
20         print(picUrl)
21 
22         picName = "%d.jpg" %i
23         urllib.request.urlretrieve(picUrl, "c:\\" + picName)
24 
25         content1 = content1[positionEnd+len(tail):]
26         i +=1
27     
28 
29 if __name__ == "__main__":
30    callFunc()

 

 

posted @ 2018-08-03 21:56  孙国光  阅读(120)  评论(0)  编辑  收藏  举报