提取存储在磁盘上的html文件的url和名称,并分别打印它们-Python

这是我需要的正确输出,但我相信有更好的方法。

import os
with open ('~/SomeFolder/page.html'),'r') as html:
    txt = html.read()
    text = txt
#for urls    
nolp = 0
urlarrow = []
while nolp == 0:
    pos = txt.find("href")
    if pos >= 0:
      txtcount = len(txt)
      txt = txt[pos:txtcount]
      pos = txt.find('"')
      txtcount = len(txt)
      txt = txt[pos+1:txtcount]
      pos = txt.find('"')
      url = txt[0:pos]
      if url.startswith("http") and url.endswith("pdf"):
          urlarrow.append(url)
    else:
      nolp = 1

with open (os.path.expanduser('~/SomeFolder/page.html'),'r') as html:
    text = html.read()

#for names  
noloop = 0
namearrow = []
while noloop == 0:
    posB = text.find("title")
    if posB >= 0:
      textcount = len(text)
      text = text[posB:textcount]
      posB = text.find('"')
      textcount = len(text)
      text = text[posB+19:textcount] #because string starts 19 chars after the posB
      posB = text.find('</')
      name = text[1:posB]
      if text[0].startswith('>'):
          namearrow.append(name)
    else:
      noloop = 1

fullarrow = []
for pair in zip(urlarrow, namearrow):
    for item in pair:
        fullarrow.append(item)
for instance in fullarrow:
    print(instance)

html.close()