编程语言
首页 > 编程语言> > 二、编程学习网站题目爬取。

二、编程学习网站题目爬取。

作者:互联网

1.访问菜鸟教程(https://www.runoob.com),爬取其Python3实例模块的题目内容,要求输出格式如下图所示。

【答案】

import requests

from lxml import etree

import time

# 获取题目链接

url = 'https://www.runoob.com/python3/python3-examples.html'

web_data = requests.get(url)   

dom = etree.HTML(web_data.text, etree.HTMLParser(encoding='utf-8'))  # 网页解析

exerciseList= dom.xpath('//div[@id="content"]/ul/li/a/text()')       # 练习题名称

urlList= dom.xpath('//div[@id="content"]/ul/li/a/@href')             # 练习题超链接

urlList = ['/python3/'+i  if '/python3/' not in i else i for i in urlList ]                               

urlList = ['https://www.runoob.com' + i if 'www.runoob.com/' not in i else 'https:'+i for i in urlList]   

exerciseString = '\n'.join(exerciseList)      # 将练习题名称拼接成一个字符串

with open('exercisePython.txt', 'w') as f:

    f.write(exerciseString)

#爬取题目数据及整理写出

resultList = []

for url in urlList:

    web_data = requests.get(url)

    dom = etree.HTML(web_data.text, etree.HTMLParser(encoding='utf-8'))  # 网页源码解析

    # 获取题目及答案

    title = dom.xpath('string(//div[@id="content"]/h1)')       # 练习题名称

    content = dom.xpath('string(//div[@id="content"]/p[2])')   # 练习题描述内容

    code = dom.xpath('string(//div[@id="content"]//div[@class="example"]//div[@class="hl-main"])')  # 练习题答案

    result = dom.xpath('string(//div[@id="content"]/p[3])')    # 结果描述

    output = dom.xpath('string(//div[@id="content"]/pre)')     # 目标输出

    res = title + '\n' + content+ '\n'   # 将内容进行拼接

    resultList.append(res)

    time.sleep(1)

    print(url, '\n', res)

mid = resultList.copy()

for i in range(len(mid)):

    mid[i] = str(i+1)+'、'+ mid[i]  # 加入题目序号

with open('Python编程基础上机题库1.txt', 'w', encoding='utf-8') as f:

    f.write('\n'.join(mid))         # 将数据写出

标签:xpath,content,题目,dom,编程,爬取,urlList,div,id
来源: https://blog.csdn.net/m0_55869026/article/details/120915113