web页面元素提取

最新推荐文章于 2024-06-14 09:24:52 发布

FrankHuang888

最新推荐文章于 2024-06-14 09:24:52 发布

阅读量195

点赞数 3

文章标签：前端 java 服务器 python

本文链接：https://blog.csdn.net/qq_33323974/article/details/136819871

版权

def main():
    inputfile = "new.html"
    outputfile = "new-url.txt"
    htmlLines = getHtmlLines(inputfile)
    imageUrls = extractImageUrls(htmlLines)
    showResults(imageUrls)
    saveResults(outputfile,imageUrls)

def getHtmlLines(htmlpath):
    f = open(htmlpath,"r",encoding='utf-8')
    ls = f.readlines()
    f.close
    return ls

def extractImageUrls(htmllist):
    urls = []
    for line in htmllist:
        url = line.split('src=')[-1].split('""')[1]
        if 'http'in url:
            urls.append(url)
    return urls

def showResults(urls):
    count = 0
    for url in urls:
        print('第{：2}个url:{}'.format(count.url))
        count += 1

def saveResults(filepath,urls):
    f = open(filepath,"w")
    for url in urls:
        f.write(url+"\n")
    f.close()

main()