挑战答题题库爬取

可参考思路

# coding:utf-8
import requests
import pymysql
from bs4 import BeautifulSoup
import time
from lxml import etree
import re

class Bank:
    def __init__(self):
        pass

    # 抓取平台1
    def getQuestionBank(self):
        url = 'http://www.bsmz.net/gongwen/805561.html'
        headers = {
            'Referer': 'http://xfxuezhang.cn/',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36'
        }

        html = requests.get(url, headers=headers).content.decode('gbk')
        tree = etree.HTML(html)
        content = tree.xpath('//div[@class="clearfix neirong"]/p/text()')
        # print(content)
        return content

    # 数据清洗
    def parseQuestions(self, content):
        # 最终的结果集
        arrays = []
        # 临时工具数组
        temp = []
        # 存选项
        options = []
        # 跳过，“选择词语的正确词形”这个题型以后再说
        skip = 0
        for i in content:
            i = i.replace('\u3000', '')
            # 答案
            if i.startswith('参考答案'):
                if skip == 1:
                    skip = 0
                    continue
                # print(i+"  "+str(temp))
                # 选项对应的数组下标
                if len(re.findall(r'[a-eA-E]', i)) == 0:
                    continue
                index = ord(re.findall(r'[a-eA-E]', i)[0].upper()) - 65
                # 选项对应的答案内容
                answer = options.pop(index)
                # print(str(len(temp))+' '+str(temp)+' '+answer)
                temp.append(re.findall(r'[a-eA-E]、{0,}(.+)', answer)[0])
                # 存入结果集
                arrays.append(temp.copy())
                # print(temp)
                # 数组清空，为下次做准备
                temp.clear()
                # 数组清空，为下次做准备
                options.clear()
            # 选项
            elif re.match(r'^[A-E]+', i):
                if skip == 1:
                    continue
                options.append(i)
            # 题干
            else:
                # 这个题型以后再说
                if '选择词语的正确词形' in i:
                    skip = 1
                    continue
                # 去除特殊字符，并加入
                temp.append((temp.pop() if len(temp) != 0 else '')+re.sub('\W+', '', i).replace("_", ''))
        # print(arrays)
        # print(len(arrays))
        return arrays

    # 数据持久化
    def storeQuestions(self, arrays):
        db = pymysql.connect(host="localhost", port=3306, user="root", passwd="1061700625", db="learn")
        cursor = db.cursor(pymysql.cursors.DictCursor)  # 使用cursor()方法获取操作游标,按字典返回
        for item in arrays:
            print('*' * 20)
            print(item)
            if len(item) < 2:
                print(">> 数据错误")
                continue
            question = item[0]
            options = None
            answer = item[1]
            sql = "select * from bank where question='{}'".format(question)
            cursor.execute(sql)
            data = cursor.fetchall()
            if len(data) != 0:
                print(">> 数据存在")
                continue
            sql = "insert into bank(question,options,answer) values('{}','{}','{}')".format(question, options, answer)
            try:
                cursor.execute(sql)  # 使用execute方法执行SQL语句
                db.commit()  # 提交到数据库执行
                print(">> 插入完成")
            except Exception as e:
                print(">> 插入失败")
                print('*' * 20 + '\r\n' + str(e) + '\r\n' + '*' * 20)
                db.rollback()  # 发生错误时回滚
        cursor.close()
        db.close()


if __name__ == '__main__':
    bank = Bank()
    content = bank.getQuestionBank()
    arrays = bank.parseQuestions(content)
    bank.storeQuestions(arrays)