爬虫系列之股票信息爬取

1. 总述

慕课中这段代码的功能是首先从东方财富网上获得所有股票的代码，再利用我们所获得的股票代码输入url中进入百度股票页面爬取该只股票的详细信息。

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


main()

2. 具体分析

2.1 获取源码

这段代码的功能就是使用requests库直接获得网页的所有源代码。

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

2.2 获取股票代码

在源码中可以看到每支股票都对应着一个6位数字的代码，这部分要做的工作就是获取这代码编号。这编号在a标签中，所有首先用BeautifulSoup选出所有的a标签，接下来我们在用attrs[href]来获取a标签的href属性值，最后用正则表达式筛选出我们想要的代码值。

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])  #findall返回的是一个列表，所有这里[0]的作用就是append一个字符串，而不是一个列表进去
        except:
            continue

2.3 获取股票信息

同样的原理，最后用字典来保存。

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]})  #text是requests的方法

            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

 

3. 增加进度条显示

进度条的显示只需要首先将count赋0，然后在下面的位置加入如下语句即可，r转译不换行。

            with open(fpath, 'a', encoding='utf-8') as f:
                f.write(str(infoDict) + '
')
                count = count+1
                print('
当前速度:{:.2f}%'.format(count*100/len(lst)), end='')
        except:
            count = count + 1
            print('
当前速度:{:.2f}%'.format(count * 100 / len(lst)), end='')
            traceback.print_exc()
            continue