python爬蟲學習 之 定向爬取 股票資訊
阿新 • • 發佈:2018-12-27
一、功能描述
目標:獲取上交所和深交所所有股票的名稱和交易 資訊
輸出:儲存到檔案中
技術路線:requests-bs4-re
二、
選取原則:股票資訊靜態存在於HTML頁面中,非js程式碼生成,沒有robots協議限制
三、程式的結構設計
1、從東方財富網獲取股票列表
2、根據股票列表逐個到百度股票獲取個股資訊
3、將結果儲存到檔案
四、
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 ""
#構造得到股票編號列表的函式
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
#構造得到股票資訊的函式
def getStockInfo(lst, stockURL, fpath):
for stock in lst:
url = stockURL + stock +".html"
html = getHTMLText(url) #得到具體單支股票頁面的html
try :
if html == "":
continue
infoDict={}
soup = BeautifulSoup(html,"html.parser")
stockInfo = soup.find("div", attrs={"class":"stock-bets"}) #找到屬性為"class":"stock-bets",名稱為div的標籤
name = stockInfo.find(attrs={"class":"bets-name"}) #在div標籤中,找到屬性為"class":"bets-name"的標籤
infoDict.update({"股票名稱":name.text.split()[0]}) #字典新增鍵值對,其中name.text為name標籤中的文字資訊,包括換行符和空字元,利用split()函式後,返回股票名字和標號的列表。
keyList = stockInfo.find_all("dt") #在div標籤中,找到所有dt標籤
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() #將具體的錯誤資訊及其所在位置打印出來
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()
五、針對上述程式碼的改進
import requests
from bs4 import BeautifulSoup
import traceback
import re
def getHTMLText(url,code='utf-8'):#加入一個形參code,設定其預設值為utf-8編碼
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = code #不需要再次通過解析正文的資訊而得到編碼
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(attrs={'class':'bets-name'})
infoDict.update({'股票名稱': 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當前速度:{:.2f}%".format(count*100/len(lst)),end="")#\r實現了列印資訊完畢後游標重新移動至開始位置。
except:
count = count + 1
print("\r當前速度:{:.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()