服务器之家

服务器之家 > 正文

Python实现爬取亚马逊数据并打印出Excel文件操作示例

时间：2021-06-27 00:20     来源/作者：刘超军

本文实例讲述了python实现爬取亚马逊数据并打印出excel文件操作。分享给大家供大家参考，具体如下：

python大神们别喷，代码写的很粗糙，主要是完成功能，能够借鉴就看下吧，我是学java的，毕竟不是学python的，自己自学看了一点点python，望谅解。

?
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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
#!/usr/bin/env python3
# encoding=utf-8
import sys
import re
import urllib.request
import json
import time
import zlib
from html import unescape
import threading
import os
import xlwt
import math
import requests
#例如这里设置递归为一百万
sys.setrecursionlimit(1000000000)
##获取所有列别
def getprourl():
  urllist = []
  headers = {"user-agent":"mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/50.0.2661.102 safari/537.36"}
  session = requests.session()
  furl="https://www.amazon.cn/?tag=baidu250-23&hvadid={creative}&ref=pz_ic_22fvxh4dwf_e&page="
  for i in range(0,1):
    html=""
    html = session.post(furl+str(i),headers = headers)
    html.encoding = 'utf-8'
    s=html.text.encode('gb2312','ignore').decode('gb2312')
    url=r'</li><li id=".*?" data-asin="(.+?)" class="s-result-item celwidget">'
    reg=re.compile(url,re.m)
    name='"category" : "' + '(.*?)' + '"'
    reg1=re.compile(name,re.s)
    urllist = reg1.findall(html.text)
    return urllist
##根据类别获取数据链接
def geturldata(ci):
   url="https://www.amazon.cn/s/ref=nb_sb_noss_2?__mk_zh_cn=%e4%ba%9a%e9%a9%ac%e9%80%8a%e7%bd%91%e7%ab%99&url=search-alias%3daps&field-keywords="+ci+"&page=1&sort=review-rank"
   return url
##定时任务,等待1秒在进行
def fun_timer():
  time.sleep(3)
##根据链接进行查询每个类别的网页内容
def getprodata(allurllist):
  webcontenthtmllist = []
  headers = {"user-agent": "mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/50.0.2661.102 safari/537.36"}
  for ci in allurllist:
    session = requests.session()
    fun_timer()
    html = session.get(geturldata(ci),headers = headers)
    # 设置编码
    html.encoding = 'utf-8'
    html.text.encode('gb2312', 'ignore').decode('gb2312')
    gxg = r'</li><li id=".*?" data-asin="(.+?)" class="s-result-item celwidget">'
    reg = re.compile(gxg, re.m)
    items = reg.findall(html.text)
    print(html.text)
    webcontenthtmllist.append(html.text)
  return webcontenthtmllist
##根据网页内容过滤需要的属性和值
def getprovalue():
  list1 = [] * 5
  list2 = [] * 5
  list3 = [] * 5
  list4 = [] * 5
  list5 = [] * 5
  list6 = [] * 5
  list7 = [] * 5
  list8 = [] * 5
  urllist = getprourl();
  urllist.remove('全部分类')
  urllist.remove('prime会员优先购')
  index = 0
  for head in urllist:
    if index >= 0 and index < 5:
      list1.append(head)
      index = index + 1
    if index >= 5 and index < 10:
      list2.append(head)
      index = index + 1
    if index >= 10 and index < 15:
      list3.append(head)
      index = index + 1
    if index >= 15 and index < 20:
      list4.append(head)
      index = index + 1
    if index >= 20 and index < 25:
      list5.append(head)
      index = index + 1
    if index >= 25 and index < 30:
      list6.append(head)
      index = index + 1
    if index >= 30 and index < 35:
      list7.append(head)
      index = index + 1
    if index >= 35 and index < 40:
      list8.append(head)
      index = index + 1
  webcontenthtmllist1 = []
  webcontenthtmllist1 = getprodata(list1)
  webcontenthtmllist2 = []
  webcontenthtmllist2 = getprodata(list2)
  webcontenthtmllist3 = []
  webcontenthtmllist3 = getprodata(list3)
  webcontenthtmllist4 = []
  webcontenthtmllist4 = getprodata(list4)
  webcontenthtmllist5 = []
  webcontenthtmllist5 = getprodata(list5)
  webcontenthtmllist6 = []
  webcontenthtmllist6 = getprodata(list6)
  webcontenthtmllist7 = []
  webcontenthtmllist7 = getprodata(list7)
  webcontenthtmllist8 = []
  webcontenthtmllist8 = getprodata(list8)
  ##存储所有数据的集合
  datatwoalllist1 = []
  print("开始检索数据,检索数据中..........")
  ##网页内容1
  for html in webcontenthtmllist1:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容2
  for html in webcontenthtmllist2:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容3
  for html in webcontenthtmllist3:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容4
  for html in webcontenthtmllist4:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容5
  for html in webcontenthtmllist5:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容6
  for html in webcontenthtmllist6:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容7
  for html in webcontenthtmllist7:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  ##网页内容8
  for html in webcontenthtmllist8:
    for i in range(15):
      datalist = []
      datalist.append(unescape(getprocategory(html,i)))
      datalist.append(unescape(getprotitle(html,i)))
      datalist.append(getproprice(html,i))
      datalist.append(getsellercount(html,i))
      datalist.append(getprostar(html,i))
      datalist.append(getprocommentcount(html,i))
      print(datalist)
      datatwoalllist1.append(datalist)
  print("检索数据完成！！！！")
  print("开始保存并打印excel文档数据！！！！")
  ##保存文档
  createtable(time.strftime("%y%m%d") + '亚马逊销量数据统计.xls', datatwoalllist1)
##抽取类别
def getprocategory(html,i):
    i = 0;
    name = '<span class="a-color-state a-text-bold">' + '(.*?)' + '</span>'
    reg=re.compile(name,re.s)
    items = reg.findall(html)
    if len(items)==0:
      return ""
    else:
      if i<len(items):
        return items[i]
      else:
        return ""
##抽取标题
def getprotitle(html,i):
  html = gethtmlbyid(html,i)
  name = '<a class="a-link-normal s-access-detail-page s-color-twister-title-link a-text-normal" target="_blank" src="/uploads/allimg/210627/0021345S7-0.png" />

打包成exe文件，直接可以点击运行：打包过程我就不一一说了，都是一些命令操作：

要安装pyinstaller，打成exe的操作命令：--inco是图标，路径和项目当前路径一样

途中遇到很多问题，都一一解决了，乱码，ip限制，打包后引入模块找不到，递归最大次数，过滤的一些问题

pyinstaller -f -c --icon=my.ico crawling.py    这是打包命令

Python实现爬取亚马逊数据并打印出Excel文件操作示例

效果图：

Python实现爬取亚马逊数据并打印出Excel文件操作示例

希望本文所述对大家python程序设计有所帮助。

原文链接：https://blog.csdn.net/qq_27026603/article/details/79712403

标签：
Python 亚马逊 Excel 爬取 

相关文章

热门资讯

2020微信伤感网名听哭了 让对方看到心疼的伤感网名大全
2020微信伤感网名听哭了 让对方看到心疼的伤感网名大全 2019-12-26
yue是什么意思 网络流行语yue了是什么梗
yue是什么意思 网络流行语yue了是什么梗 2020-10-11
背刺什么意思 网络词语背刺是什么梗
背刺什么意思 网络词语背刺是什么梗 2020-05-22
苹果12mini价格表官网报价 iPhone12mini全版本价格汇总
苹果12mini价格表官网报价 iPhone12mini全版本价格汇总 2020-11-13
2021德云社封箱演出完整版 2021年德云社封箱演出在线看
2021德云社封箱演出完整版 2021年德云社封箱演出在线看 2021-03-15
返回顶部