python 爬虫简单案例

import urllib.request;
import re;

\'\'\'
爬取指定地址的页面内容
\'\'\'
def getHtmlCode(url):
    page = urllib.request.urlopen(url)
    htmlCode = page.read()
    return htmlCode.decode(\'utf-8\')

# htmlCon = getHtml("https://tieba.baidu.com/p/1753935195")
# htmlCon = htmlCon.decode(\'utf-8\')
# pageFile = open("xh.txt", \'w\')
# pageFile.write(htmlCon)
# pageFile.close()

\'\'\'
获取页面内的所有图片并下载到本地
\'\'\'
def getImg(htmlCode):
    reg = r\'src="(.+?\.jpg)" width\'
    regImg = re.compile(reg)
    imgList = regImg.findall(htmlCode)
    x = 0
    for img in imgList:
        urllib.request.urlretrieve(img, \'%s.jpg\' % x)
        x += 1

# htmlCode = getHtmlCode("https://tieba.baidu.com/p/1753935195")
# htmlCode = htmlCode.decode(\'utf-8\')

print(u\'---------网页图片抓取------------\')
print(u\'请输入url:\')
url = input()
if url:
    pass
else:
    print(u\'---------没有输入地址，使用默认地址。--------\')
    url = "https://tieba.baidu.com/p/1753935195"

print(u\'-------正在抓取网页----------\')
htmlCode = getHtmlCode(url);

print(u\'-------正在下载图片---------\')
getImg(htmlCode);

print(u\'-------下载图片完成-------\')
input(\'Press Enter to exit\')
print(\'hello world\')

 学习来源：https://www.cnblogs.com/Axi8/p/5757270.html  贴吧图片爬取