自学python之爬虫2

Posted 2020-10-06

这次爬取的是淘宝网，通过关键词搜索后，获取结果中商品的名称和价格

 1 import requests
 2 import re
 3 
 4 #获取页面
 5 def getHTMLText(url):
 6     try:
 7         r = requests.get(url, timeout=30)
 8         r.raise_for_status()
 9         r.encoding = r.apparent_encoding
10         return r.text
11     except:
12         return "get fail"
13 
14 #解析页面
15 def parsePage(ilt, html):
16     try:
17         plt = re.findall(r‘\\"view_price\\"\\:\\"[\\d\\.]*\\"‘,html) #商品价格
18         tlt = re.findall(r‘\\"raw_title\\"\\:\\".*?\\"‘,html) #商品名称
19         for i in range(len(plt)):
20             price = eval(plt[i].split(‘:‘)[1])
21             title = eval(tlt[i].split(‘:‘)[1])
22             ilt.append([price , title])
23     except:
24         print(‘parse fail‘)
25 
26 #输出商品信息
27 def printGoodsList(ilt):
28     tplt = "{:4}\\t{:8}\\t{:16}"
29     print(tplt.format("序号", "价格", "商品名称"))
30     count = 0
31     for g in ilt:
32         count = count + 1
33         print(tplt.format(count, g[0], g[1]))
34 
35 #主函数
36 def main():
37     goods = ‘书包‘ #搜索关键词
38     depth = 2 #搜索深度，即页数
39     start_url = ‘https://s.taobao.com/search?q=‘ + goods
40     infoList = []
41     for i in range(depth):
42         try:
43             url = start_url + ‘&s=‘ + str(44*i)
44             html = getHTMLText(url)
45             parsePage(infoList, html)
46         except:
47             continue
48     printGoodsList(infoList)
49 
50 main()

 

结果：