新浪股市雷达

标签：pymysql   find   and   main   spider   __name__   mys   date   ada   

#-*- coding:utf-8 -*-

import requests
import chardet
from bs4 import BeautifulSoup

‘‘‘
import tushare as ts
import pandas as pd
import pymysql
import lxml
import time
import datetime
import os
import random
pymysql.install_as_MySQLdb()
from sqlalchemy import create_engine
from lxml import etree
‘‘‘
‘‘‘
爬取新浪股市雷达
‘‘‘
def sina_Spider():
    for page_num in range(1,16):
        url = ‘http://finance.sina.com.cn/stockradar/stockradar‘ + str(page_num) + ‘.html‘
        headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0"}

        html = requests.get(url=url,headers=headers)
        html.encoding = html.apparent_encoding

        soup = BeautifulSoup(html.text,‘lxml‘)
        #tr_list = soup.select(‘.tbl_wrap > table > tbody > tr‘)
        tr_list1 = soup.find_all(‘tr‘)
        for idx, tr in enumerate(tr_list1):
            if idx != 0:
                tds = tr.find_all(‘th‘)
                change_time = tds[0].string
                stkcode = tds[1].string
                stkname = tds[2].string
                type_value = tds[3].string
                data =
                sql = ‘‘‘insert ignore into stock.***(date,stkcode,stkname,change_time,type_value) values (%s,%s,%s,%s,%s)‘‘‘
                print(change_time)
                print(stkcode)
                print(stkname)
                print(type_value)


if __name__ == "__main__":

    ‘‘‘
    ts.set_token(‘ac16b470869c5d82db5033ae9288f77b282d2b5519507d6d2c72fdd7‘)
    pro = ts.pro_api()
    # 1、数据库参数
    conn = pymysql.connect(host=‘127.0.0.1‘, port=3308, user=‘root‘, password=‘abc123‘, db=‘zlcpy_db‘, charset=‘utf8‘)
    print(conn)

    # 2、创建操作的游标
    cursor = conn.cursor()
    ‘‘‘

    # 调用函数
    sina_Spider()

新浪股市雷达

标签：pymysql   find   and   main   spider   __name__   mys   date   ada   

原文地址：https://www.cnblogs.com/Iceredtea/p/11717418.html