Python实现遍历url

# coding:utf-8
import re
import requests
import xlrd
from xlutils.copy import copy

class Traversal_Web:
def __init__(self):
    pass
def url(self,path,sites):
    # 获取网页内容
    #pqyload = {name:source}
    #site="http://XXX"
    i=0
    r = requests.get(sites)
    data = r.text
    # 利用正则查找所有连接
    link_list =re.findall(r"(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')" ,data)
    for url in link_list:
        i=i+1
        if url.startswith("http://") or url.startswith("https://"):
            r = requests.get(url)
            url=r.url
            status=r.status_code
        else:
            url = url
            status='xxx'
        self.write_xls(path,url,i,0)
        self.write_xls(path,status,i,1)

def write_xls(self,path,text,nrow,ncol):
    rb=xlrd.open_workbook(path)
    rs = rb.sheet_by_index(0)
    wb = copy(rb)
    ws = wb.get_sheet(0)
    ws.write(nrow, ncol,text)
    wb.save(path)