web页面元素提取

def main():
    inputfile = "new.html"
    outputfile = "bar.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:
        if 'img' in line:
            url = line.split('src=')[-1].split('"')[1]
            if 'https' in url:
                urls.append(url)
    #print(urls)
    return urls

def showResults(urls):
    count = 1
    for url in urls:
       #print("第{ }个URL:{ }".format(count,url))
       print(url)
       count += 1

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

main()