例 股票数据定向爬虫
功能描述
- 目标:获取上交所和深交所所有股票的名称和交易信息
- 价格等
- 输出:保存到文件中
- 技术路线:requests-bs4-re
- 候选网站
- http://finance.sina.com.cn/stock/
- https://gupiao.baidu.com/stock/
- quote.eastmoney.com/stocklist.html/
- 选取原则:股票信息静态存在于HTML页面中,非js代码生成,没有Robots协议限制
- 浏览器F12,源代码查看
- 选取心态:不要纠结于某个网站,多找信息源
import requests
from bs4 import BeautifulSoup
import traceback
import re
def getHTMLText(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
def getStockList(lst,stockHTML)
html = getHTMLText(stockURL)
soup = BeautifulSoup(html, 'html.parser')
a = soup.find_all('a')
for i in a:
try: # 筛选
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 = {}
soupt = Beautifulsoup(html,'html.parser')
stockInfo = soup.find('div', attrs={'class':'stock-bets'})
name = stckInfo.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
value = valueList[i].text
infoDict[key] = value
with open(fpath,'a',encoding='utf-8') as f:
f.write(str(infoDict) + '\n')
except:
traceback.print_exc()
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()
优化
速度提高:编码识别的优化
def getHTMLText(url,code='utf-8'):
try:
r.requests.get(url)
r.raise_for_status
r.encoding = code
return r.text
except:
return ""
体验提高:增加动态进度显示
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