本文实例为大家分享了python爬取淘宝商品的具体代码,供大家参考,具体内容如下
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
import requests as req import re def getHTMLText(url): try : r = req.get(url, timeout = 30 ) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except : return "" def parasePage(ilt, html): try : plt = re.findall(r '\"view_price\"\:\"[\d\.]*\"' , html) tlt = re.findall(r '\"raw_title\"\:\".*?\"' , html) for i in range ( len (plt)): price = eval (plt[i].split( ':' )[ 1 ]) title = eval (tlt[i].split( ':' )[ 1 ]) ilt.append([price, title]) except : print ("") def printGoodsList(ilt): tplt = "{:4}\t{:8}\t{:16}" print (tplt. format ( "序列号" , "价格" , "商品名称" )) count = 0 for j in ilt: count = count + 1 print (tplt. format (count, j[ 0 ], j[ 1 ])) def main(): depth = 3 start_url = 'https://s.taobao.com/search?q=' + goods infoList = [] for i in range (depth): try : url = start_url + '&s=' + str ( 44 * i) html = getHTMLText(url) parasePage(infoList, html) except : continue printGoodsList(infoList) main() |
效果图:
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。
原文链接:http://blog.csdn.net/oliverkingli/article/details/78037864