python3抓取淘宝网零食页面信息

 1 import requests
 2 import re
 3 
 4 def get_html_text(url):
 5     try:
 6         r = requests.get(url, timeout=30)
 7         r.raise_for_status()
 8         r.encoding = 'utf-8'
 9         return r.text
10     except:
11         return ""
12 
13 def parse_page(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 def clear_content(filename):
25     f = open(filename, 'w')
26     f.truncate()
27     f.close()
28 
29 def save_goods(filename, goods_list):
30     pattern = "{:4}\t{:8}\t{:16}"
31     with open(filename, 'a', encoding='utf-8') as f:
32         f.write(pattern.format("序号", "价格", "商品名称") + '\n')
33         count = 0
34         for goods in goods_list:
35             count = count + 1
36             f.write(pattern.format(count, goods[0], goods[1]) + '\n')
37     f.close()
38 
39 def main():
40     goods = '零食'
41     depth = 2
42     start_url = 'http://s.taobao.com/search?q=' + goods
43     goods_list = []
44     for i in range(depth):
45         try:
46             url = start_url + '&s=' + str(44*i)
47             html = get_html_text(url)
48             parse_page(goods_list, html)
49         except:
50             continue
51     filename = "taobao_snacks.txt"
52     clear_content(filename)
53     save_goods(filename, goods_list)
54     print("商品信息已保存到taobao_snacks.txt")
55 
56 main()

转载于:https://www.cnblogs.com/songfei90/p/10523126.html