python crawler web page

 npm install  or pip install 插件

import json
import time
from openpyxl import load_workbook
from pip._vendor import requests
from bs4 import BeautifulSoup
import pandas as pd
import re
import xlsxwriter

設置request header

header = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ' 'Chrome/112.0.0.0 Safari/537.36'

定義

exl_name = "abc.xlsx"
sheetname ="sheet_doc"

pandas讀取Excel的URL

pdExl = pd.read_excel("abc.xlsx", engine="openpyxl",index_col=0,usecols='A:Q')

結果寫入Excel

workbook   = xlsxwriter.Workbook('abc.xlsx')

worksheet = workbook.add_worksheet('contract')

requests抓取，BeautifulSoup分析

通過Regex提取核心內容

for index, _row in pdExl.iterrows():
    if _row['url'] is None:
        continue
    url = 'https://www.abc.com'+_row['url']