Python爬虫入门（五）股票案例

一、股票案例

import requests
from bs4 import BeautifulSoup
import traceback
import re


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


def ge_stock_list(lst, stockURL):
    html = get_html_text(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 ge_stock_info(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock + ".html"
        html = get_html_text(url)
        try:
            if html == "":
                continue
            infoDict = {}  # 每支股票的信息
            soup = BeautifulSoup(html, 'html.parser')
            # div为标签名 定位到属性class值为stock-bets的第一个div
            stockInfo = soup.find('div', attrs={'class': 'stock-bets'})
            # name为stockInfo中class属性值为bets-name的第一个标签
            name = stockInfo.find_all(attrs={'class': 'bets-name'})[0]
            # name.text为标签中间的文字
            # update方法将某个字典加入到另一个字典中
            infoDict.update({'股票名称': name.text.split()[0]})
            # 在stockInfo代表的div标签下找到所有dt标签即股票的属性名
            keyList = stockInfo.find_all('dt')
            # 在stockInfo代表的div标签下找到所有dd标签即股票的属性值
            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()
            continue


def main():
    stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'BaiduStockInfo.txt'
    slist = []
    ge_stock_list(slist, stock_list_url)
    ge_stock_info(slist, stock_info_url, output_file)

二、改进版

import requests
from bs4 import BeautifulSoup
import traceback
import re


def ge_html_text(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""


def ge_stock_list(lst, stockURL):
    html = ge_html_text(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 ge_stock_info(lst, stockURL, fpath):
    count = 0
    for stock in lst:
        url = stockURL + stock + ".html"
        html = ge_html_text(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 = 'BaiduStockInfo.txt'
    slist = []
    ge_stock_list(slist, stock_list_url)
    ge_stock_info(slist, stock_info_url, output_file)


main()