本文主要是介绍爬取第一试卷网高三数学试卷并下载到本地，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
import requests
import re
import os
filename = '试卷\\'
if not os.path.exists(filename):os.mkdir(filename)
url = 'https://www.shijuan1.com/a/sjsxg3/list_727_1.html'
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
response = requests.get(url=url,headers=headers)
response.encoding = response.apparent_encoding
href_list = re.findall("<td width='52%' height='23'><a href=\"(.*?)\" class=\"title\" target='_blank'>",response.text)
title_list = re.findall("class=\"title\" target='_blank'>(.*?)</a>",response.text)
# https://www.shijuan1.com/a/sjywg3/243565.html
for title,href in zip(title_list,href_list):href = 'https://www.shijuan1.com'+hrefdata_html = requests.get(url=href,headers=headers)data_html.encoding = data_html.apparent_encodingdata_url = 'https://www.shijuan1.com'+re.findall('<li><a href="(.*?)" target="_blank">本地下载</a></li>',data_html.text)[0]doc = requests.get(url=data_url,headers=headers).contentwith open('试卷\\'+title+'.rar',mode='wb') as f:f.write(doc)结果展现：
改进代码：
import requests
import os
import redef get_html_data(url):headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"}response = requests.get(url=url,headers=headers)response.encoding = response.apparent_encodingreturn responsedef get_analyse_html(response):href_list = re.findall("<td width='52%' height='23'><a href=\"(.*?)\" class=\"title\" target='_blank'>",response.text)title_list = re.findall("class=\"title\" target='_blank'>(.*?)</a>", response.text)return title_list,href_listdef save(title_list,doc_list):filename = '试卷\\'if not os.path.exists(filename):os.mkdir(filename)for title,doc in zip(title_list,doc_list):with open('试卷\\' + title + '.rar', mode='wb') as f:f.write(doc)print(f'{title}已经下载完成')def get_doc(href_list):doc_list = []for href in href_list:href = 'https://www.shijuan1.com' + hrefdoc_html = get_html_data(href)data_url = 'https://www.shijuan1.com' + re.findall('<li><a href="(.*?)" target="_blank">本地下载</a></li>', doc_html.text)[0]doc = get_html_data(data_url).contentdoc_list.append(doc)return doc_listif __name__ == '__main__':url = 'https://www.shijuan1.com/a/sjsxg3/list_727_1.html'response = get_html_data(url)title_list,href_list = get_analyse_html(response)doc_list = get_doc(href_list)save(title_list,doc_list)进一步写成类：
import requests
import os
import re
class save_doc():def get_html_data(self,href):headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"}response = requests.get(url=href, headers=headers)response.encoding = response.apparent_encodingreturn responsedef get_analyse_html(self,response):href_list = re.findall("<td width='52%' height='23'><a href=\"(.*?)\" class=\"title\" target='_blank'>",response.text)title_list = re.findall("class=\"title\" target='_blank'>(.*?)</a>", response.text)return title_list, href_listdef save(self,title_list,doc_list):filename = '试卷\\'if not os.path.exists(filename):os.mkdir(filename)for title, doc in zip(title_list, doc_list):with open('试卷\\' + title + '.rar', mode='wb') as f:f.write(doc)print(f'{title}已经下载完成')def get_doc(self,href_list):doc_list = []for href in href_list:href = 'https://www.shijuan1.com' + hrefdoc_html = self.get_html_data(href)data_url = 'https://www.shijuan1.com' + re.findall('<li><a href="(.*?)" target="_blank">本地下载</a></li>', doc_html.text)[0]doc = self.get_html_data(data_url).contentdoc_list.append(doc)return doc_list
save = save_doc()
response = save.get_html_data('https://www.shijuan1.com/a/sjsxg3/list_727_1.html')
title_list,href_list = save.get_analyse_html(response)
doc_list = save.get_doc(href_list)
save.save(title_list,doc_list)对于类还是很不熟，我想要类中的方法返回的值，可以直接传入类中的其他方法，应该怎么写呢？我想要写一个类，传入一个url,直接下载所需要的数据，即最终代码为
save = save_doc("https://www.shijuan1.com/a/sjsxg3/list_727_1.html")不需要上面那么复杂的传来传去，应该怎么做呢？
这篇关于爬取第一试卷网高三数学试卷并下载到本地的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
