python爬取亚马逊书籍信息代码分享

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
import requests
import sys
import re
import pymysql

class product:
  type="历史"
  name=""
  author=""
  desciption=""
  pic1=""
  languages=""
  press=""

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/gp/search/ref=sr_adv_b/?search-alias=stripbooks&field-binding_browse-bin=2038564051&sort=relevancerank&page="
  for i in range(1,7):
    html=""
    print(furl+str(i)) 
    html = session.post(furl+str(i)+'&node=658418051',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)
    items = reg.findall(html.text)
    for i in range(0,len(items)):
      urlList.append(items[i])
  urlList=set(urlList)
  return urlList

def getProData(url):
  pro = product()
  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()
  zurl="https://www.amazon.cn/dp/"
  html = session.get(zurl+url,headers = headers)
  html.encoding = 'utf-8'
  s=html.text.encode('gb2312','ignore').decode('gb2312')
  pro.pic1=getProPic(html)
  pro.name=getProName(html)
  pro.author=getProAuthor(html)
  pro.desciption=getProDescrip(html)
  pro.press=getProPress(html)
  pro.languages=getProLanguages(html)
  return pro

def getProPic(html):
  pic=r'id="imgBlkFront" data-a-dynamic-image="{"(.+?)".*?}"'
  reg=re.compile(pic,re.M)
  items = reg.findall(html.text)
  if len(items)==0:
    return ""
  else:
    return items[0]

def getProName(html):
  name=r'<div class="ma-title"><p class="wraptext goto-top">(.+?)<span'
  reg=re.compile(name,re.M)
  items = reg.findall(html.text)
  if len(items)==0:
    return ""
  else:
    return items[0]

def getProAuthor(html):
  author=r'<span class="author.{0,20}" data-width="".{0,30}>.*?<a class="a-link-normal" href=".*?books" rel="external nofollow" >(.+?)</a>.*?<span class="a-color-secondary">(.+?)</span>'
  reg=re.compile(author,re.S)
  items = reg.findall(html.text)
  au=""
  for i in range(0,len(items)):
    au=au+items[i][0]+items[i][1]
  return au

def getProDescrip(html):
  Descrip=r'<noscript>.{0,30}<div>(.+?)</div>.{0,30}<em></em>.{0,30}</noscript>.{0,30}<div id="outer_postBodyPS"'
  reg=re.compile(Descrip,re.S)
  items = reg.findall(html.text)
  if len(items)==0:
    return ""
  else:
    position = items[0].find('海报：')
    descrip=items[0]
    if position != -1:
      descrip=items[0][0:position]
    return descrip.strip()

def getProPress(html):
  press=r'<li><b>出版社:</b>(.+?)</li>'
  reg=re.compile(press,re.M)
  items = reg.findall(html.text)
  if len(items)==0:
    return ""
  else:
    return items[0].strip()


def getProLanguages(html):
  languages=r'<li><b>语种：</b>(.+?)</li>'
  reg=re.compile(languages,re.M)
  items = reg.findall(html.text)
  if len(items)==0:
    return ""
  else:
    return items[0].strip()

def getConnection():
  config = {
     'host':'121.**.**.**',
     'port':3306,
     'user':'root',
     'password':'******',
     'db':'home_work',
     'charset':'utf8',
     'cursorclass':pymysql.cursors.DictCursor,
     }
  connection = pymysql.connect(**config)
  return connection

urlList = getProUrl()
i = 0
for d in urlList:
  i = i + 1
  print (i)
  connection = getConnection()
  pro = getProData(d)
  try:
    with connection.cursor() as cursor:
      sql='INSERT INTO books (type,name,author,desciption,pic1,languages,press) VALUES (%s,%s,%s,%s,%s,%s,%s)'
      cursor.execute(sql,(pro.type,pro.name,pro.author,pro.desciption,pro.pic1,pro.languages,pro.press))
    connection.commit()
  finally:
    connection.close();