python爬虫实战：爬取股票信息，对上交所和深交所所有的股票信息进行搜集

要用到两个网站：
1.获取所有股票的名称的网址（这里指上交所和深交所的股票）
https://www.banban.cn/gupiao/list_sz.html


2.获取单个股票的各类信息
https://gupiao.baidu.com/stock/股票名称.html

 

---

'''
要用到两个网站：
1.获取所有股票的名称的网址（这里指上交所和深交所的股票）
https://www.banban.cn/gupiao/list_sz.html


2.获取单个股票的各类信息
https://gupiao.baidu.com/stock/股票名称.html
'''

import requests
from bs4 import BeautifulSoup
import traceback
import re

#获取网页内容
def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""


#获取所有的股票名称，将其放在一个列表中
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"\d{6}", href)[0])
        except:
            continue


def getStockInfo(lst, stockURL, fpath):
    count = 0
    for stock in lst:
        url = stockURL + "sz" + stock + ".html"#对应的每只股票的网址
        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

#保存到本地，并加载进度条
            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://www.banban.cn/gupiao/list_sz.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()