服务器之家

服务器之家 > 正文

Python爬取当当、京东、亚马逊图书信息代码实例

时间：2020-12-23 00:37     来源/作者：吴祥生

注：1.本程序采用MSSQLserver数据库存储，请运行程序前手动修改程序开头处的数据库链接信息

2.需要bs4、requests、pymssql库支持

3.支持多线程

?
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
from bs4 import BeautifulSoup
import re,requests,pymysql,threading,os,traceback
 
try:
  conn = pymysql.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='book',charset="utf8")
  cursor = conn.cursor()
except:
  print('\n错误：数据库连接失败')
 
#返回指定页面的html信息
def getHTMLText(url):
  try:
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
    r = requests.get(url,headers = headers)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    return r.text
  except:
    return ''
#返回指定url的Soup对象
def getSoupObject(url):
  try:
    html = getHTMLText(url)
    soup = BeautifulSoup(html,'html.parser')
    return soup
  except:
    return ''
#获取该关键字在图书网站上的总页数
def getPageLength(webSiteName,url):
  try:
    soup = getSoupObject(url)
    if webSiteName == 'DangDang':
      a = soup('a',{'name':'bottom-page-turn'})
      return a[-1].string
    elif webSiteName == 'Amazon':
      a = soup('span',{'class':'pagnDisabled'})
      return a[-1].string
  except:
    print('\n错误：获取{}总页数时出错...'.format(webSiteName))
    return -1
 
class DangDangThread(threading.Thread):
  def __init__(self,keyword):
    threading.Thread.__init__(self)
    self.keyword = keyword
  def run(self):
    print('\n提示：开始爬取当当网数据...')
    count = 1
   
    length = getPageLength('DangDang','http://search.dangdang.com/?key={}'.format(self.keyword))#总页数
    tableName = 'db_{}_dangdang'.format(self.keyword)
 
    try:
      print('\n提示：正在创建DangDang表...')
      cursor.execute('create table {} (id int ,title text,prNow text,prPre text,link text)'.format(tableName))
      print('\n提示：开始爬取当当网页面...')
      for i in range(1,int(length)):
        url = 'http://search.dangdang.com/?key={}&page_index={}'.format(self.keyword,i)
        soup = getSoupObject(url)
        lis = soup('li',{'class':re.compile(r'line'),'id':re.compile(r'p')})
        for li in lis:
          a = li.find_all('a',{'name':'itemlist-title','dd_name':'单品标题'})
          pn = li.find_all('span',{'class': 'search_now_price'})
          pp = li.find_all('span',{'class': 'search_pre_price'})
 
          if not len(a) == 0:
            link = a[0].attrs['href']
            title = a[0].attrs['title'].strip()
          else:
            link = 'NULL'
            title = 'NULL'
 
          if not len(pn) == 0:
            prNow = pn[0].string
          else:
            prNow = 'NULL'
 
          if not len(pp) == 0:
            prPre = pp[0].string
          else:
            prPre = 'NULL'
          sql = "insert into {} (id,title,prNow,prPre,link) values ({},'{}','{}','{}','{}')".format(tableName,count,title,prNow,prPre,link)
          cursor.execute(sql)
          print('\r提示：正在存入当当数据,当前处理id：{}'.format(count),end='')
          count += 1
          conn.commit()
    except:
      pass
 
class AmazonThread(threading.Thread):
  def __init__(self,keyword):
    threading.Thread.__init__(self)
    self.keyword = keyword
 
  def run(self):
    print('\n提示：开始爬取亚马逊数据...')
    count = 1
    length = getPageLength('Amazon','https://www.amazon.cn/s/keywords={}'.format(self.keyword))#总页数
    tableName = 'db_{}_amazon'.format(self.keyword)
     
    try:
      print('\n提示：正在创建Amazon表...')
      cursor.execute('create table {} (id int ,title text,prNow text,link text)'.format(tableName))
   
      print('\n提示：开始爬取亚马逊页面...')
      for i in range(1,int(length)):
        url = 'https://www.amazon.cn/s/keywords={}&page={}'.format(self.keyword,i)
        soup = getSoupObject(url)
        lis = soup('li',{'id':re.compile(r'result_')})
        for li in lis:
          a = li.find_all('a',{'class':'a-link-normal s-access-detail-page a-text-normal'})
          pn = li.find_all('span',{'class': 'a-size-base a-color-price s-price a-text-bold'})
          if not len(a) == 0:
            link = a[0].attrs['href']
            title = a[0].attrs['title'].strip()
          else:
            link = 'NULL'
            title = 'NULL'
 
          if not len(pn) == 0:
            prNow = pn[0].string
          else:
            prNow = 'NULL'
 
          sql = "insert into {} (id,title,prNow,link) values ({},'{}','{}','{}')".format(tableName,count,title,prNow,link)
          cursor.execute(sql)
          print('\r提示：正在存入亚马逊数据,当前处理id：{}'.format(count),end='')
          count += 1
          conn.commit()
    except:
      pass
 
class JDThread(threading.Thread):
  def __init__(self,keyword):
    threading.Thread.__init__(self)
    self.keyword = keyword
  def run(self):
    print('\n提示：开始爬取京东数据...')
    count = 1
 
    tableName = 'db_{}_jd'.format(self.keyword)
     
    try:
      print('\n提示：正在创建JD表...')
      cursor.execute('create table {} (id int,title text,prNow text,link text)'.format(tableName))
      print('\n提示：开始爬取京东页面...')
      for i in range(1,100):
        url = 'https://search.jd.com/Search?keyword={}&page={}'.format(self.keyword,i)
        soup = getSoupObject(url)
        lis = soup('li',{'class':'gl-item'})
        for li in lis:
          a = li.find_all('div',{'class':'p-name'})
          pn = li.find_all('div',{'class': 'p-price'})[0].find_all('i')
 
          if not len(a) == 0:
            link = 'http:' + a[0].find_all('a')[0].attrs['href']
            title = a[0].find_all('em')[0].get_text()
          else:
            link = 'NULL'
            title = 'NULL'
           
          if(len(link) > 128):
            link = 'TooLong'
 
          if not len(pn) == 0:
            prNow = '￥'+ pn[0].string
          else:
            prNow = 'NULL'
          sql = "insert into {} (id,title,prNow,link) values ({},'{}','{}','{}')".format(tableName,count,title,prNow,link)
          cursor.execute(sql)
          print('\r提示：正在存入京东网数据,当前处理id：{}'.format(count),end='')
          count += 1
          conn.commit()
    except :
      pass
def closeDB():
  global conn,cursor
  conn.close()
  cursor.close()
 
def main():
  print('提示：使用本程序，请手动创建空数据库：Book，并修改本程序开头的数据库连接语句')
  keyword = input("\n提示：请输入要爬取的关键字：")
 
  dangdangThread = DangDangThread(keyword)
  amazonThread = AmazonThread(keyword)
  jdThread = JDThread(keyword)
   dangdangThread.start()
  amazonThread.start()
  jdThread.start()
  dangdangThread.join()
  amazonThread.join()
  jdThread.join()
   closeDB()
   print('\n爬取已经结束，即将关闭....')
  os.system('pause')
   
main()

示例截图：

关键词：Android下的部分运行结果（以导出至Excel）

Python爬取当当、京东、亚马逊图书信息代码实例

Python爬取当当、京东、亚马逊图书信息代码实例

Python爬取当当、京东、亚马逊图书信息代码实例

总结

以上就是本文关于Python爬取当当、京东、亚马逊图书信息代码实例的全部内容，希望对大家有所帮助。如有不足之处，欢迎留言指出。感谢朋友们对本站的支持！

原文链接：http://blog.csdn.net/yuanlaijike/article/details/65936197

标签：
Python 爬虫 

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
Intellij idea2020永久破解，亲测可用！！！
Intellij idea2020永久破解，亲测可用！！！ 2020-07-29
歪歪漫画vip账号共享2020_yy漫画免费账号密码共享
歪歪漫画vip账号共享2020_yy漫画免费账号密码共享 2020-04-07
电视剧《琉璃》全集在线观看 琉璃美人煞1-59集免费观看地址
电视剧《琉璃》全集在线观看 琉璃美人煞1-59集免费观看地址 2020-08-12
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
返回顶部