010 Python网络爬虫与信息提取 股票数据定向爬虫

[A]股票数据定向爬虫实例介绍

  功能描述

    目标:获取上交所和深交所所有股票的名称和交易信息

    输出:保存到文件中

  候选网站:

    1. 新浪股票:https://finance.sina.com.cn/

    2. 百度股票:https://gupiao.baidu.com/stock/

  候选网站选取:

    选取原则:互票信息静态的存储于HTML页面中,而非js代码生成,没有robots协议限制

    选取方法:浏览器F12,源代码查看

    选取心态:不纠结于某个网站,多找信息源尝试

   程序设计

    步骤1:从东方财富网获取股票信息列表

    步骤2:根据股票列表诸葛到百度股票获取个股信息

    步骤3:将结果存储于到文件中

[B] 股票数据定向爬虫实例编写

# CrawBaiduStocksA.py
import requests
from bs4 import BeautifulSoup
import traceback
import re


def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""


def getStockList(lst, stockURL):
    html = getHTMLText(stockURL)
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]d{6}", href)[0])
        except:
            continue


def getStockInfo(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div', attrs={'class': 'stock-bets'})

            name = stockInfo.find_all(attrs={'class': 'bets-name'})[0]
            infoDict.update({'股票名称': name.text.split()[0]})

            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val

            with open(fpath, 'a', encoding='utf-8') as f:
                f.write(str(infoDict) + '
')
        except:
            traceback.print_exc()
            continue


def main():
    stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist = []
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)


main()
View Code
原文地址:https://www.cnblogs.com/carreyBlog/p/14018585.html