淘宝商品与股票数据爬虫实战

在学过正则表达式后，跟着老师实战了下“淘宝商品比价定向爬虫”和“股票数据定向爬虫”这两个。

一开始我想了下，思路好迷糊，不好从哪下手。在看了老师的教程后，才慢慢的理解了。下面是代码与效果

淘宝商品比价定向爬虫：

 1 import requests
 2 import re
 3
 4 def getHTMLText(url):
 5     try:
 6         r = requests.get(url, timeout = 30)
 7         r.raise_for_status()
 8         r.encoding = r.apparent_encoding
 9         return r.text
10     except:
11         return ""
12
13 def parsePage(ilt, html):
14     try:
15         plt = re.findall(r‘\"view_price\"\:\"[\d\.]*\"‘,html)
16         tlt = re.findall(r‘\"raw_title\"\:\".*?\"‘,html)
17         for i in range(len(plt)):
18             price = eval(plt[i].split(‘:‘)[1])
19             title = eval(tlt[i].split(‘:‘)[1])
20             ilt.append([price, title])
21     except:
22         print("")
23
24
25 def printGoodsList(ilt):
26     tplt = "{:4}\t{:8}\t{:16}"
27     print(tplt.format("序号","价格","商品名称"))
28     count = 0
29     for g in ilt:
30         count += 1
31         print(tplt.format(count, g[0], g[1]))
32
33 def main():
34     goods = ‘acm‘
35     depth = 2
36     start_url = ‘https://s.taobao.com/search?q=‘ + goods
37     infoList = []
38     for i in range(depth):
39         try:
40             url = start_url + ‘&s=‘ + str(44*i)
41             html = getHTMLText(url)
42             parsePage(infoList, html)
43         except:
44             continue
45     printGoodsList(infoList)
46
47 main()

下面是效果：

股票数据定向爬虫：

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import traceback
 4 import re
 5
 6 def getHTMLText(url, code="utf-8"):
 7     try:
 8         r = requests.get(url)
 9         r.raise_for_status()
10         r.encoding = code
11         return r.text
12     except:
13         return ""
14
15 def getStockList(lst, stockURL):
16     html = getHTMLText(stockURL, "GB2312")#由于知道网站编码,就可以直接赋值进去，如果用r.status_encoding的话时间更久些
17     soup = BeautifulSoup(html, ‘html.parser‘)
18     a = soup.find_all(‘a‘)
19     for i in a:
20         try:
21             href = i.attrs[‘href‘]
22             lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
23         except:
24             continue
25
26 def getStockInfo(lst, stockURL, fpath):
27     count = 0
28     for stock in lst:
29         url = stockURL + stock + ".html"
30         html = getHTMLText(url)
31         try:
32             if html=="":
33                 continue
34             infoDict = {}
35             soup = BeautifulSoup(html, ‘html.parser‘)
36             stockInfo = soup.find(‘div‘,attrs={‘class‘:‘stock-bets‘})
37
38             name = stockInfo.find_all(attrs={‘class‘:‘bets-name‘})[0]
39             infoDict.update({‘股票名称‘: name.text.split()[0]})
40
41             keyList = stockInfo.find_all(‘dt‘)
42             valueList = stockInfo.find_all(‘dd‘)
43             for i in range(len(keyList)):
44                 key = keyList[i].text
45                 val = valueList[i].text
46                 infoDict[key] = val
47
48             with open(fpath, ‘a‘, encoding=‘utf-8‘) as f:
49                 f.write( str(infoDict) + ‘\n‘ )
50                 count = count + 1
51                 print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
52         except:
53             count = count + 1
54             print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
55             continue
56
57 def main():
58     stock_list_url = ‘http://quote.eastmoney.com/stocklist.html‘
59     stock_info_url = ‘https://gupiao.baidu.com/stock/‘
60     output_file = ‘E:/BaiduStockInfo.txt‘
61     slist=[]
62     getStockList(slist, stock_list_url)
63     getStockInfo(slist, stock_info_url, output_file)
64
65 main()

效果的话先放这个吧，爬取时间有点慢