使用Python进行Web页面元素提取

博客冲浪

于 2021-08-25 19:41:55 发布

阅读量567

点赞数

分类专栏： Python 文章标签： python

本文链接：https://blog.youkuaiyun.com/m0_56497861/article/details/119918114

版权

Python 专栏收录该内容

6 篇文章

订阅专栏

#gethtmllines() extractimageurls()  showresults()  saveresults()
def main():
    inputfile='nationalgeograhic.html'
    outputfile='nationalgeographic.txt'
    htmllines=gethtmllines(inputfile)
    imageurls=extractimageurls(htmllines)
    showresults(imageurls)
    saveresults(imageurls,outputfile)
def gethtmllines(filename):
    f=open(filename,'r',encoding='utf-8')
    txt=f.readlines()
    f.close()
    return txt
def extractimageurls(htmllines):
    urls=[]
    for line in htmllines:
        if 'img' in line:
            url=line.split('src=')[-1]
            if 'http' in url:
                urls.append(url)
    return urls
def showresults(urls):
    count=1
    for url in urls:
        print('第{0}个URL:{1}'.format(count,url))
        count+=1
def saveresults(urls,outputfile):
    f=open(outputfile,'w')
    for url in urls:
        f.write(url+'\n')
    f.close()
main()