ICode9

精准搜索请尝试: 精确搜索
首页 > 编程语言> 文章详细

Python爬虫学习笔记(实例:股票信息定向爬虫及优化)

2020-01-22 21:41:18  阅读:70  来源: 互联网

标签:count Python html 爬虫 url lst 实例 find stock


#要求URL对应的股票数据显性的填充在HTML代码中

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        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_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="") #不换行动态进度条
        except:
            count = count + 1
            print("\r当前进度: {:.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()
二叉叔 发布了22 篇原创文章 · 获赞 12 · 访问量 1万+ 私信 关注

标签:count,Python,html,爬虫,url,lst,实例,find,stock
来源: https://blog.csdn.net/qq_33360009/article/details/104072697

专注分享技术,共同学习,共同进步。侵权联系[admin#icode9.com]

Copyright (C)ICode9.com, All Rights Reserved.

ICode9版权所有