python爬虫爬取网页资源

import time import requests from bs4 import BeautifulSoup from openpyxl import Workbook headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36' } # 爬虫[Requests设置请求头Headers],伪造浏览器 # 核心爬取代码 url = 'https://www.basketball-reference.com/leagues/NBA_2014_games-december.html' params = {"show_ram": 1} response = requests.get(url, params=params, headers=headers) # 访问url outwb = Workbook() #声明Workbook outws = outwb.worksheets[0] # 定义excel 的sheet soup = BeautifulSoup(response.text, 'html.parser') # 获取网页源代码 tr = soup.find('tbody').find_all('tr') # .find定位到所需数据位置 .find_all查找所有的tr（表格） # 去除标签栏 outws.append(['Date','Start(ET)','Visitor/Neutral','PTS','Home/Neutral','PTS','','Attend.','Arena','Notes']) for j in tr[1:]: # tr2[1:]遍历第1列到最后一列，表头为第0列 listData = [] # 定义数组 th = j.find_all('th') # th表格 thDate = th[0].get_text().strip() listData.append(thDate) tds = j.find_all('td') # td表格 for k in tds[0:]: tdDate = k.get_text().strip() listData.append(tdDate) outws.append(listData) outwb.save(r'test.xlsx')