- 程序来源:中国大学MOOC网《网络爬虫与信息提取课程》。
- 程序目的:获取上交所和深交所的部分股票信息,输出到文件。
- 涉及知识;requests库、BeautifulSoup库和re库
import requests
from bs4 import BeautifulSoup
import re
def getHTMLText(url, code="utf-8"):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = code # 直接指定用utf-8解码
return r.text
except:
return ""
def getStockList(lst, stockURL):
html = getHTMLText(stockURL, "GB2312") # 东方财富网用的是GB2312编码
soup = BeautifulSoup(html, 'html.parser')
a = soup.find_all('a')[:200] # 股票代码在a标签中的href属性中。我们只取前100个a标签
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 + stock # 每只股票的信息的链接
html = getHTMLText(url)
try:
if html == "":
continue
infoDict = {} # 每只股票的信息都存在字典中
soup = BeautifulSoup(html, 'html.parser')
stockInfo = soup.find('div', attrs={'class': 'stock-info'})
name = stockInfo.find_all(attrs={'class': 'stock-name'})[0]
infoDict.update({'股票名称': name.text.split()[0]}) # .text可以取出标签中的字符串
keyList = stockInfo.find_all('dt')[:4] # 只取股票的前4个信息
valueList = stockInfo.find_all('dd')[:4]
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="") # \r表示返回到当前行的起始位置,打印的内容会覆盖之前打印的内容
# 每次print之后,会自动换行。end用来取消自动换行。
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/stock_list.html' # 从东方财富网获取每只股票的代码
stock_info_url = 'https://www.laohu8.com/stock/' # 从老虎社区网站获取每只股票的信息
output_file = 'BaiduStockInfo.txt'
slist = []
getStockList(slist, stock_list_url)
getStockInfo(slist, stock_info_url, output_file)
main()