0.网页分析
想必大家应该不是第一次爬取数据了,对于F12开发者工具有了一定了解,所以这里就不再赘述了。对于数据来源,别执着于一个网站,可以多分析几个网站来选择相对爬取简单的网站来进行数据的爬取。
1.流程分析
百度股票的URL: http://gupiao.baidu.com/stock/sh502036.html
分析可得:只需将东方财富网中的 .html前的股票代码提取出来并加入到 https://gupiao.baidu.com/stock/的后面,便可以得到所有股票源数据。
2.函数设定
3.完整代码
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]) # 匹配类似sh000001的股票代码
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="") # \r:能让输出比例时不自动换行
except:
count = count + 1
print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
continue
def main():
stock_list_url = '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()
本练习来自中国大学MOOC