小白学 Python 爬虫（25）：爬取股票信息

def get_stock_list(stockListURL):

    r =requests.get(stockListURL, headers = headers)

    doc = PyQuery(r.text)

    list = []

    # 获取所有 section 中 a 节点，并进行迭代

    for i in doc('.stockTable a').items():

        try:

            href = i.attr.href

            list.append(re.findall(r"\d{6}", href)[0])

        except:

            continue

    list = [item.lower() for item in list]  # 将爬取信息转换小写

    return list

将上面的链接当做参数传入，大家可以自己运行下看下结果，小编这里就不贴结果了，有点长。。。

获取详情数据

详情的数据看起来好像是在页面上的，但是，实际上并不在，实际最终获取数据的地方并不是页面，而是一个数据接口。

http://qd.10jqka.com.cn/quote.php?cate=real&type=stock&callback=showStockDate&return=json&code=000001

至于是怎么找出来，小编这次就不说，还是希望各位想学爬虫的同学能自己动动手，去寻找一下，多找几次，自然就摸到门路了。

现在数据接口有了，我们先看下返回的数据吧：

showStockDate({"info":{"000001":{"name":"\u5e73\u5b89\u94f6\u884c"}},"data":{"000001":{"10":"16.13","8":"16.14","9":"15.87","13":"78795234.00","19":"1262802470.00","7":"16.12","15":"40225508.00","14":"37528826.00","69":"17.73","70":"14.51","12":"5","17":"945400.00","264648":"0.010","199112":"0.062","1968584":"0.406","2034120":"9.939","1378761":"16.026","526792":"1.675","395720":"-948073.000","461256":"-39.763","3475914":"313014790000.000","1771976":"1.100","6":"16.12","11":""}}})

很明显，这个结果并不是标准的 json 数据，但这个是 JSONP 返回的标准格式的数据，这里我们先处理下头尾，将它变成一个标准的 json 数据，再对照这页面的数据进行解析，最后将分析好的值写入数据库中。

def getStockInfo(list, stockInfoURL):

    count = 0

    for stock in list:

        try:

            url = stockInfoURL + stock

            r = requests.get(url, headers=headers)

            # 将获取到的数据封装进字典

            dict1 = json.loads(r.text[14: int(len(r.text)) - 1])

            print(dict1)

            # 获取字典中的数据构建写入数据模版

            insert_data = {

                "code": stock,

                "name": dict1['info'][stock]['name'],

                "jinkai": dict1['data'][stock]['7'],

                "chengjiaoliang": dict1['data'][stock]['13'],

                "zhenfu": dict1['data'][stock]['526792'],

                "zuigao": dict1['data'][stock]['8'],

                "chengjiaoe": dict1['data'][stock]['19'],

                "huanshou": dict1['data'][stock]['1968584'],

                "zuidi": dict1['data'][stock]['9'],

                "zuoshou": dict1['data'][stock]['6'],

                "liutongshizhi": dict1['data'][stock]['3475914']

            }

            cursor.execute(sql_insert, insert_data)

            conn.commit()

            print(stock, '：写入完成')

        except:

            print('写入异常')

            # 遇到错误继续循环

            continue

这里我们加入异常处理，因为本次爬取的数据有些多，很有可能由于某些原因抛出异常，我们当然不希望有异常的时候中断数据抓取，所以这里添加异常处理继续抓取数据。

完整代码

我们将代码稍作封装，完成本次的实战。

import requests

import re

import json

from pyquery import PyQuery

import pymysql

# 数据库连接

def connect():

    conn = pymysql.connect(host='localhost',

                           port=3306,

                           user='root',

                           password='password',

                           database='test',

                           charset='utf8mb4')

    # 获取操作游标

    cursor = conn.cursor()

    return {"conn": conn, "cursor": cursor}

connection = connect()

conn, cursor = connection['conn'], connection['cursor']

sql_insert = "insert into stock(code, name, jinkai, chengjiaoliang, zhenfu, zuigao, chengjiaoe, huanshou, zuidi, zuoshou, liutongshizhi, create_date) values (%(code)s, %(name)s, %(jinkai)s, %(chengjiaoliang)s, %(zhenfu)s, %(zuigao)s, %(chengjiaoe)s, %(huanshou)s, %(zuidi)s, %(zuoshou)s, %(liutongshizhi)s, now())"

headers = {

    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'

}

def get_stock_list(stockListURL):

    r =requests.get(stockListURL, headers = headers)

    doc = PyQuery(r.text)

    list = []

    # 获取所有 section 中 a 节点，并进行迭代

    for i in doc('.stockTable a').items():

        try:

            href = i.attr.href

            list.append(re.findall(r"\d{6}", href)[0])

        except:

            continue

    list = [item.lower() for item in list]  # 将爬取信息转换小写

    return list

def getStockInfo(list, stockInfoURL):

    count = 0

    for stock in list:

        try:

            url = stockInfoURL + stock

            r = requests.get(url, headers=headers)

            # 将获取到的数据封装进字典

            dict1 = json.loads(r.text[14: int(len(r.text)) - 1])

            print(dict1)

            # 获取字典中的数据构建写入数据模版

            insert_data = {

                "code": stock,

                "name": dict1['info'][stock]['name'],

                "jinkai": dict1['data'][stock]['7'],

                "chengjiaoliang": dict1['data'][stock]['13'],

                "zhenfu": dict1['data'][stock]['526792'],

                "zuigao": dict1['data'][stock]['8'],

                "chengjiaoe": dict1['data'][stock]['19'],

                "huanshou": dict1['data'][stock]['1968584'],

                "zuidi": dict1['data'][stock]['9'],

                "zuoshou": dict1['data'][stock]['6'],

                "liutongshizhi": dict1['data'][stock]['3475914']

            }

            cursor.execute(sql_insert, insert_data)

            conn.commit()

            print(stock, '：写入完成')

        except:

            print('写入异常')

            # 遇到错误继续循环

            continue

def main():

    stock_list_url = 'https://hq.gucheng.com/gpdmylb.html'

    stock_info_url = 'http://qd.10jqka.com.cn/quote.php?cate=real&type=stock&callback=showStockDate&return=json&code='

    list = get_stock_list(stock_list_url)

    # list = ['601766']

    getStockInfo(list, stock_info_url)

if __name__ == '__main__':

    main()

成果

最终小编耗时 15 分钟左右，成功抓取数据 4600+ 条，结果就不展示了。

示例代码

本系列的所有代码小编都会放在代码管理仓库 Github 和 Gitee 上，方便大家取用。

示例代码-Github

示例代码-Gitee

巴特西

小白学 Python 爬虫（25）：爬取股票信息

引言

分析

实战

获取股票代码列表

获取详情数据

完整代码

成果

示例代码

最新文章

热门文章