简单爬虫常用
#获取网络内容 def getWebContent(url): headers = {‘User-Agent‘:‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11‘} req = urllib2.Request(url, headers=headers) html = urllib2.urlopen(req).read() return html #下载图片 def downloadImage(imageUrl,localName): data = urllib2.urlopen(imageUrl).read() fi=open(localName,‘wb‘) fi.write(data) fi.close()
时间: 2024-10-09 09:46:32