python爬虫小样+csv文件的存储

from bs4 import BeautifulSoup as bsp import requests import re import csv #从页面抓取相应的内容 i = 549 titles3 = [] while i > 538: urls = "http://www.view.sdu.edu.cn/xyxw/" + str(i) + ".htm" page_response = requests.get(urls, timeout = 5) page_content = bsp(page_response.content,"html.parser") for sublist in page_content.find_all(class_ = "sublist"): titles = sublist.find_all("li") titles3 += [title.text for title in titles] i -= 1 titles4 = str(titles3) titles5=titles4.replace(",","\n") temp = [] time_t = [] #将抓取的文件存入.txt文件 with open("viewsdu5.txt", mode = "w", encoding = "utf-8") as f: f.write(titles5) f.close() #对字符串进行处理，首先根据日期（正则表达式）分开 #第二部将字符串中的逗号变为回车，从而将内容分层 with open("viewsdu5.txt", mode = "r", encoding = "utf-8") as f: for i in f.readlines(): str = (re.search(r"(\d{4}-\d{1,2}-\d{1,2})",i)) str1 = str.group(0) time_t.append(str1) titles6 = i.replace(str1, " ") temp.append(titles6) f.close() #存入最终格式为.csv文件（表格）,需要先将数据进行分组 with open("viewsdu5.txt", mode = "w", encoding = "utf-8") as f: for i in temp: f.write(i) f.close() headers = ["内容", "时间"] rows = [] for (tem,tim) in zip(temp,time_t): rows.append([tem,tim]) #将列表存入，该列表是n行2列的列表 with open("csv01.csv", "w", newline='') as f: f_csv = csv.writer(f) f_csv.writerow(headers) for row in rows: f_csv.writerow(row) f.close() #summary：1、先按照需求信息爬取网站内容 # 2、对所有的信息进行字符串处理，也就是所谓数据清洗的工作。