python 爬虫 实现增量去重和定时爬取

前言： 在爬虫过程中，我们可能需要重复的爬取同一个网站，为了避免重复的数据存入我们的数据库中 通过实现增量去重 去解决这一问题 本文还针对了那些需要实时更新的网站 增加了一个定时爬取的功能；

本文作者同开源中国（殊途同归_）；

解决思路： 1.获取目标url

                   2.解析网页

                    3.存入数据库（增量去重）

                     4.异常处理

                      5.实时更新（定时爬取）

下面为数据库的配置 mysql_congif.py： 

import pymysql


def insert_db(db_table, issue, time_str, num_code):
    host = '127.0.0.1'
    user = 'root'
    password = 'root'
    port = 3306
    db = 'lottery'
    data_base = pymysql.connect(host=host, user=user, password=password, port=port, db=db)
    cursor = data_base.cursor()
    try:
        sql = "INSERT INTO %s VALUES ('%s','%s','%s')" % (db_table, issue, time_str, num_code)
        cursor.execute(sql)
        data_base.commit()
    except ValueError as e:
        print(e)
        data_base.rollback()
    finally:
        cursor.close()
        data_base.close()


def select_db(issue, db_table):
    host = '127.0.0.1'
    user = 'root'
    password = 'root'
    port = 3306
    db = 'lottery'
    data_base = pymysql.connect(host=host, user=user, password=password, port=port, db=db)
    cursor = data_base.cursor()
    try:
        sql = "SELECT '%s' FROM %s " % (issue, db_table)
        cursor.execute(sql)
        data_base.commit()
    except ValueError as e:
        print(e)
        data_base.rollback()
    finally:
        return issue

接下来是主要代码 test.py：

#  使用bs4进行网页解析
#  实现了增量去重
#  实现了定时爬取
import datetime
import time

from bs4 import BeautifulSoup
import requests


from mysql_config import insert_db
from mysql_config import select_db


def my_test():
    db_table = 'lottery_table'
    url = 'http://kj.13322.com/kl10_dkl10_history_dtoday.html'
    res = requests.get(url)
    content = res.content
    soup = BeautifulSoup(content, 'html.parser', from_encoding='utf8')
    c_t = soup.select('#trend_table')[0]
    trs = c_t.contents[4:]
    for tr in trs:
        if tr == '\n':
            continue
        tds = tr.select('td')
        issue = tds[1].text
        time_str = tds[0].text
        num_code = tr.table.text.replace('\n0', ',').replace('\n', ',').strip(',')
        print('期号：%s\t时间：%s\t号码:%s' % (str(issue), str(time_str), str(num_code)))
        issue_db = select_db(issue, db_table)
        try:
            if issue_db == issue:
                insert_db(db_table, issue_db, time_str, num_code)
                print('添加%s到%s成功' % (issue_db, db_table))
        except Exception as e:
            print('%s 已经存在！' % issue_db)
            print(e)


if __name__ == '__main__':
    flag = 0
    now = datetime.datetime.now()
    sched_time = datetime.datetime(now.year, now.month, now.day, now.hour, now.minute, now.second) +\
                 datetime.timedelta(seconds=3)
    while True:
        now = datetime.datetime.now()
        if sched_time < now:
            time.sleep(3)
            print(now)
            my_test()
            flag = 1
        else:
            if flag == 1:
                sched_time = sched_time + datetime.timedelta(minutes=2)
                flag = 0