python学习------正则表达式总结（爬虫实例）

用python实现一个简单的爬虫，爬取百度贴吧图片

1.安装python库

import urllib.request
import re

2.挖掘网页内容
网址： https://tieba.baidu.com/p/4814458788
目的：对本网址中的图片进行抓取
对网页源代码挖掘发现图片的url格式为：

3.根据url获取网页内容

def getHtml(url):
    page=urllib.request.urlopen(url)
    html=page.read()
    return html

4.从html中解析图片的url(使用正则表达式)

def getJPGs(html):
    jpg = r'<img.*?src="(.*?jpg)" size' #只取（）里的字符串
    html = html.decode('utf-8')  #编码
    jpgs = re.findall(jpg, html)
    return jpgs

5.总体代码

import urllib.request
import re


# 根据url获取网页html内容
def getHtmlContent(url):
    page = urllib.request.urlopen(url)
    html=page.read()
    return html

def getJPGs(html):
    # 解析jpg图片url的正则
    jpgReg = r'<img.*?src="(.*?jpg)" size' #只取（）里的字符串
    html = html.decode('utf-8')
    jpgs = re.findall(jpgReg, html)
    return jpgs


# 用图片url下载图片并保存成制定文件名
def downloadJPG(imgUrl, fileName):
    urllib.request.urlretrieve(imgUrl, fileName)


# 批量下载图片，默认保存到当前目录下
def batchDownloadJPGs(imgUrls, path='./'):
    # 用于给图片命名
    count = 1
    for url in imgUrls:
        downloadJPG(url, ''.join([path, '{0}.jpg'.format(count)]))
        count = count + 1

# 封装：从百度贴吧网页下载图片
def download(url):
    html = getHtmlContent(url)
    jpgs = getJPGs(html)
    batchDownloadJPGs(jpgs)


def main():
    url = 'https://tieba.baidu.com/p/4814458788'
    download(url)


if __name__ == '__main__':
    main()