读取一个网页的源代码:
import urllib.request
def getHtml(url):
html=urllib.request.urlopen(url).read()
return html
print(getHtml("http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%A3%81%E7%BA%B8&ct=201326592&lm=-1&v=flip"))
利用正则表达式爬取一个网页上的图片地址:
import re
import urllib.request
def getHtml(url):
html=urllib.request.urlopen(url).read()
return html
def getImg(html):
r=r'"thumbURL":"(http://img.+?\.jpg)"' #定义正则
imglist=re.findall(r,html)
return imglist
html=str(getHtml("http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%A3%81%E7%BA%B8&ct=201326592&lm=-1&v=flip"))
print(getImg(html))
运行结果: