python爬虫学习 之 定向爬取 股票信息

一、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

技术路线：requests-bs4-re

二、
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

三、程序的结构设计
1、从东方财富网获取股票列表
2、根据股票列表逐个到百度股票获取个股信息
3、将结果存储到文件

四、

import requests
from bs4 import BeautifulSoup
import traceback
import re


def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#构造得到股票编号列表的函数
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

#构造得到股票信息的函数
def getStockInfo(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock +".html"
        html = getHTMLText(url) #得到具体单支股票页面的html
        try:
            if html == "":
                continue
            infoDict={}
            soup = BeautifulSoup(html,"html.parser")
            stockInfo = soup.find("div", attrs={"class":"stock-bets"}) #找到属性为"class":"stock-bets"，名称为div的标签

            name = stockInfo.find(attrs={"class":"bets-name"}) #在div标签中，找到属性为"class":"bets-name"的标签
            infoDict.update({"股票名称":name.text.split()[0]}) #字典添加键值对，其中name.text为name标签中的文本信息，包括换行符和空字符，利用split（）函数后，返回股票名字和标号的列表。

            keyList = stockInfo.find_all("dt")  #在div标签中，找到所有dt标签
            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")
        except:
            traceback.print_exc() #将具体的错误信息及其所在位置打印出来
            continue


def main():
    stock_list_url = "http://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()

五、针对上述代码的改进

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url,code='utf-8'):#加入一个形参code，设置其默认值为utf-8编码
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code #不需要再次通过解析正文的信息而得到编码
        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(attrs={'class':'bets-name'})

            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当前速度:{:.2f}%".format(count*100/len(lst)),end="")#\r实现了打印信息完毕后光标重新移动至开始位置。
        except:
            count = count + 1
            print("\r当前速度:{:.2f}%".format(count*100/len(lst)),end="")
            continue

def main():
    stock_list_url = 'http://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()