简单的爬虫实现效果原网址:
爬到本地
代码比较简单,直接上代码
#!/usr/bin/env python
# _*_ coding:utf-8 _*_
#
# @Author : lyx
import urllib.parse
import urllib.request
import re
#获取网页代码文本,并且返回图片链接数组
def getHtml():
url = "http://www.973.com/z32670"
htmlcode = urllib.request.urlopen(url)
htmlText = htmlcode.read().decode("utf-8")#获取html内容并且解码为utf-8
print(htmlText)
#reg = r' src="(.+?\.jpg)"'
reg='<img.*?src="(http.*?)"'
plist = re.findall(reg, htmlText, re.S)#匹配图片链接
print(plist)
return plist
def downImg(plist):
print("开始下载网页图片。。。。。。。。")
i = 0
for url in plist:
if int(len(url)) > 2000:
continue
else:
f = open(r"F:\img" + '/' + str(i) + '.jpg', 'wb')
req = urllib.request.urlopen(url)
htmlText = req.read()
f.write(htmlText)
#f.close()
i += 1
print("下载完成")
plist=getHtml()
downImg(plist)
这样一个简单的爬虫爬取图片就完成了