网络爬虫信息提取实战之股票数据15

 

#导入各种需要用到的库
import requests
from bs4 import BeautifulSoup
import traceback
import re
# 定义第一个函数，获取网页的数据
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "getHTMLText函数异常"
# 定义第二个函数，对获取到的网页数据处理，循环遍历
def getStockList(lst,stockURL):
    html = getHTMLText(stockURL)
    # BeautifulSoup具有解析遍历维护标签树的功能
    soup = BeautifulSoup(html,'html.parser')
    # 查找所有的a标签，返回列表
    a = soup.find_all('a')
    # 遍历列表
    for i in a:
        try:
            # 返回属性是href的值
            href = i.attrs['href']
            # 对值进行正则匹配，符合的添加到列表当中
            lst.append(re.findall(r"[s][hz]\d{6}",href)[0])
        except:
            # 如果异常继续
            continue
# 定义第三个函数
def getStockInfo(lst,stockURL,fpath):
    # 遍历各个股票代码
    for stock in lst:
        # 各个股票的详情页
        url = stockURL + stock + ".html"
        # 获取页面信息
        html = getHTMLText(url)
        try:

            if html =='':
                continue
            # 创建空字典
            infoDict = {}
            soup = BeautifulSoup(html,'html.parser')
            # 查找div标签，并且属性是'class':'stock-bets'的第一个标签
            stockInfo = soup.find('div',attrs={'class':'stock-bets'})
            # 返回列表，属性是'class':'bets-name'的所有标签的第一个标签
            name = stockInfo.find_all(attrs={'class':'bets-name'})[0]
            #将股票名称添加到字典中，这的.text和.string有区别，区别是当有子孙节点时.string不能返回值
            infoDict.update({'股票名称':name.text.split()[0]})
            # 查找所有的信息名称和值
            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            # 遍历信息名称和值并且添加到字典中，存放到文件当中
            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')
                    # 进度条，命令行才可以看到
                    count = count+1
                    print('\r当前速度：{:.2f}%'.format(count*100/len(lst)),end='')
        except:
            count = count + 1
            print('\r当前速度：{:.2f}%'.format(count * 100 / len(lst)), end='')
            traceback.print_exc()
            continue

def main():
    stock_list_url = ""
    stock_info_url = ""
    output_file = 'E:\pycharmProjects\pachonglianxi\StockInfo.txt'
    slist = []
    getStockList(slist,stock_list_url)
    getStockInfo(slist,stock_info_url,output_file)

main()