Python3.x：定时获取页面数据存入数据库

Python3.x：定时获取页面数据存入数据库

#间隔五分钟采集一次数据入库
import pymysql
import urllib.request
from bs4 import BeautifulSoup
import threading
import time

# 数据入库处理
def doDataWlpc(jjdm, jjmc, dwjz, dwjzrq):
    r_code = 0
    print('基金信息：' + jjdm + ',' + jjmc + ',' + dwjz + ',' + dwjzrq)
    try:
        # 打开数据库连接
        conn = pymysql.connect(host='localhost', user='root',
                               passwd='lizm', db='pythondb', port=3306, charset='utf8')
        # 获取一个游标
        cursor = conn.cursor()
        # 查询数据是否已经存在
        sql_check = """SELECT * FROM pythondb.t_x01_wlpc WHERE dwjz='""" + \
            dwjz + """' and dwjzrq='""" + dwjzrq + """';"""
        print('sql_check>>>:' + sql_check)
        cursor.execute(sql_check)
        results = cursor.fetchall()
        # 判断是否有记录数
        if len(results) == 0:
            check_code = 0
        else:
            check_code = 1

        if check_code == 0:
            sql = """INSERT INTO pythondb.t_x01_wlpc (jjdm,jjmc,dwjz,dwjzrq,oprdate) VALUES('""" + \
                jjdm + """','""" + jjmc + """','""" + dwjz + \
                """','""" + dwjzrq + """',sysdate());"""
            try:
                print('sql>>>:' + sql)
                # 执行sql语句
                cursor.execute(sql)
                # 提交到数据库执行
                conn.commit()
                r_code = 0
            except:
                # 如果发生错误则回滚
                conn.rollback()
                r_code = 1
        else:
            r_code = 0
            print('基金' + jjmc + '数据已存在')
        cursor.close()  # 关闭游标
        conn.close()  # 释放数据库资源
    except:
        r_code = 1
        print("失败,异常")

    return r_code


# 获取基金的信息
def getJjInfor(header_, url_):
    # 返回数组
    r_info = []

    req = urllib.request.Request(url=url_, headers=header_)
    res = urllib.request.urlopen(req)
    html = res.read().decode('utf-8')
    soup = BeautifulSoup(html, 'html.parser')

    # css的class获取值
    jjdm = soup.find(
        'div', class_='fundDetail-tit').find('span', class_='ui-num')
    r_info.append(jjdm.get_text())
    #print('基金代码：' + jjdm.get_text())

    title_name = soup.find('div', class_='fundDetail-tit')
    r_info.append(title_name.text.split('(')[0])
    #print('基金名称：' + title_name.text.split('(')[0])

    # 获取估算净值、单位净值、累计净值
    for dataNums in soup.find_all('dd', class_='dataNums'):
        for jzs_ in dataNums.find_all('span', class_='ui-font-large ui-color-red ui-num'):
            r_info.append(jzs_.text)
            #print('' + jzs_.text)

    gz_gztime = soup.find(id='gz_gztime')
    r_info.append(gz_gztime.text.replace('(', '').replace(')', ''))
    #print('估算净值日期：' + gz_gztime.text.replace('(', '').replace(')', ''))

    # 输出class为'dataItem02'标签里面的第一个p元素
    dwjzrq_s = soup.find('dl', class_='dataItem02').p
    r_info.append(dwjzrq_s.text.split('(')[1].split(')')[0])
    #print('单位净值日期：' + dwjzrq_s.text.split('(')[1].split(')')[0])

    return r_info
 
def main():
    global timer
    url = r'http://fund.eastmoney.com/340007.html?spm=search'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}

    jj_infor = []
    jj_infor = getJjInfor(headers, url)

    print(jj_infor)

    return_code = doDataWlpc(jj_infor[0], jj_infor[1], jj_infor[3], jj_infor[5])
    if return_code ==0:
        print('执行成功')
    else:
        print('执行失败')

    #重复构造定时器
    timer = threading.Timer(5*60,main)
    timer.start()

# 测试
if __name__ == '__main__':
    #定时调度
    timer = threading.Timer(1,main)
    timer.start()
    

稍后再加上指定时间段内执行；

 

转载于:https://www.cnblogs.com/lizm166/p/8159516.html