python实现多个网站站内链接批量导出

gig919

于 2020-02-05 10:49:52 发布

阅读量884

点赞数

本文链接：https://blog.youkuaiyun.com/gig919/article/details/104179394

版权

本例多个网站的网址保存在”D:\test.xlsx”文件中第一列，代码运行结束后第二列导出站内链接，链接名保存在第三列，以下代码已经在Python27中调试通过：

#coding=utf-8
import requests
import os

from bs4 import BeautifulSoup
from openpyxl import Workbook
from openpyxl import load_workbook
from requests import exceptions

def get_html(url):
    '''
    headers = {
        'User-Agent': 'Mozilla/5.0(Macintosh; Intel Mac OS X 10_11_4)\
    AppleWebKit/537.36(KHTML, like Gecko) Chrome/52 .0.2743. 116 Safari/537.36'
    } #模拟浏览器访问
    '''
    headers = {
        'User-Agent': 'Mozilla/5.0(Windows NT 10.0; WOW64; Trident/7.0; rv:11.0)\
    like Gecko'
    }  # 模拟浏览器访问
    t1=30
    try:
        r = requests.get(url,timeout=t1, headers = headers)       #请求访问网站
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        #print(r.status_code)
        if r.status_code == 200:
           return r.text