Python爬虫之正则表达式——股票数据定向爬虫

1、目标：获取上交所和深交所所有股票的名称和交易信息

2、输出：保存到文件中

3、技术路线：requests-bs4-re

4、网页选取原则：股票信息静态存在于HTML页面中，非js代码生成，没有Robots协议限制

5、选取方法：浏览器F12，源代码查看等

6、步骤：

①从东方财富网获取股票列表

②根据股票列表组个到百度股票获取个股信息

③将结果存储到文件

以下是MOOC的源代码，但是由于时间问题，这个代码已经不能用了，但是很有参考价值

import requests
from bs4 import BeautifulSoup
import traceback
import re
 
def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""
 
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL, "GB2312")
    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):
    count = 0
    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) + '\n' )
                count = count + 1
                print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            count = count + 1
            print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
            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()

东方财富网股票列表网址：http://quote.eastmoney.com/stock_list.html
这是网页部分源码

个股信息我们可以在中财网获取：“http://quote.cfi.cn/quote_”+股票代码+".html"
这是我门需要提取的信息

以下是我重新编写的代码

import re
import requests
from bs4 import BeautifulSoup
import traceback

def getHtmlText(url):
    try:
        r = requests.get(url)
        r.encoding = 'utf-8'
        r.raise_for_status()
        return r.text
    except:
        traceback.print_exc()

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

def getStockInfo(list,stockIurl,path):
    count = 0
    for i in list[81:195]:
        try:
            code=re.findall(r'\d{6}',i)           # findall返回一个列表类型
            url = stockIurl + str(code[0]) + ".html"
            html=getHtmlText(url)
            if html=="":
                continue
            soup=BeautifulSoup(html,"html.parser")
            InfoDict={}
            na=soup.find('div',attrs={"id": "act_quote"})
            if na is None:
                continue
            name=na.find('div',attrs={'class':'Lfont'}).string
            InfoDict.update({'股票名称':name})
            Information=na.find('table',attrs={'id':'quotetab'})      # find_all返回一个列表类型
            # information=na.find('td',attrs={'class':'Rlist'})
            tds=Information.find_all('td')
            for item in tds:
                text=item.get_text()
                t_split=re.split('：|:',text)
                key = t_split[0]
                val = t_split[1]
                real_val = re.search(r'(-?\d+.?\d*[%|手|万|元]?)|(--)|(正无穷大)', val).group(0)
                InfoDict[key] = real_val

            with open(path, 'a', encoding='utf-8') as f:
                f.write(str(InfoDict) + '\n')
            count = count + 1
            print('\r当前速度：{:.2f}%'.format(count * 100 / len(list)), end="")
        except:
            count = count + 1
            print('\r当前速度：{:.2f}%'.format(count * 100 / len(list)), end="")
            traceback.print_exc()
            continue



def main():
    stock_list_url = 'http://quote.eastmoney.com/stock_list.html'
    stock_info_url = 'http://quote.cfi.cn/quote_'
    file_path = 'D://StockInfo1.txt'
    InfoList=[]
    getStockList(InfoList,stock_list_url)
    getStockInfo(InfoList,stock_info_url,file_path)

main()

getStockInfo()函数中的部分代码参考了以下这篇文章
https://blog.csdn.net/Guanhai1617/article/details/104123303