jd3/downpage.py at master · bebeter/jd3 · GitHub

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
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import sys
import urllib
import time
import os
from selenium import webdriver
from selenium.webdriver.common.action_chains import  ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )
driver=webdriver.Chrome()


def getBrand():

    #brand
    ##J_selector > div.J_selectorLine.s-brand > div > div.sl-ext > a.sl-e-more.J_extMore
    driver.find_elements_by_xpath('//*[@id="J_selector"]/div[1]/div/div[3]/a')[0].click()
    time.sleep(3)
    brands=driver.find_elements_by_xpath('//ul[@class="J_valueList v-fixed"]/li/a')
    print len(brands)
    for b in range(0,len(brands)):
        #print brands[b].text()
        html =driver.execute_script("return arguments[0].innerHTML;", brands[b])
        print html


def getLink():
    pro_links=driver.find_elements_by_tag_name('a')
    f2=open("alldata.txt","a")
    #WebElement
    print len(pro_links)
    lasturl=""
    for link in pro_links:
        link_url=str(link.get_attribute('href'))
        if link_url.find("item")>1:
            if link_url.find("comment") <0:
                if link_url==lasturl:
                    continue
                else:
                    lasturl = link_url
                    print link_url
                    f2.write(link_url+"\n")
    f2.close()

def moveWindow():

    driver.execute_script("window.scrollTo(0, document.body.scrollHeight/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*2/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*3/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*4/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*5/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*6/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*7/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*8/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*9/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*7/10)")
    time.sleep(3)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*5/10)")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight*3/10)")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-800);")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-200);")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-600);")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-300);")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-400);")
    time.sleep(1)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight-500);")
    #将页面滚动条拖到底部
    js="var q=document.documentElement.scrollTop=10000"
    driver.execute_script(js)
    time.sleep(3)

    #将滚动条移动到页面的顶部
    js="var q=document.documentElement.scrollTop=10"
    driver.execute_script(js)
    time.sleep(3)

def main():
    #获取参数
    url="https://search.jd.com/Search?keyword=%E7%9F%B3%E6%96%9B&enc=utf-8&wq=%E7%9F%B3%E6%96%9B&pvid=ntlc2oui.8o37qo"#sys.argv[1]
    #url="https://item.jd.com/1124152398.html"
    #操作IE

    #driver = webdriver.Firefox()
    driver.get(url)
    print driver.page_source

    driver.maximize_window()
    moveWindow()


    #driver.find_element_by_xpath("//*[@id='wrapper_wrapper']").send_keys(Keys.DOWN)


    f2=open('D:\jdpro'+'\\page\\1.html',"a")
    f2.write(driver.page_source)
    f2.close()

    #翻页
    #driver.find_element_by_class_name("fp-next").click()
    #print driver.page_source
    for i in range(0,34):
        driver.find_element_by_class_name("fp-next").send_keys(Keys.ARROW_RIGHT)
        moveWindow()
        time.sleep(3)
        print driver.page_source
        time.sleep(3)
        f2=open('D:\jdpro'+'\\page\\'+str(i)+'.html',"a")
        f2.write(driver.page_source)
        f2.close()
        getLink()


    #创建目录


    if 2>1 :
        return
    dir_name='t'
    print dir_name
    root_dir='d:\\img'
    dir_name=root_dir+'\\'+dir_name
    dir_name=dir_name.replace('|','-')
    if(os.path.exists(root_dir)!=True):
        os.mkdir(root_dir)
    if(os.path.exists(dir_name)!=True):
        os.mkdir(dir_name)
    images=driver.find_elements_by_tag_name('img')
    count=0
    #cheeses = driver.find_elements(By.CLASS_NAME, "p-parameter")
    cheeses = driver.find_elements_by_class_name("p-parameter")
    ActionChains(driver).move_to_element(cheeses)
    print(len(images))
    for image in images:
        im=driver.find_elements_by_partial_link_text(str(image.get_attribute('src')))

        count=count+1
        image_url=str(image.get_attribute('src'))


        if image_url is None :
            print count,image_url,"1"
            continue
        else:
            print count,image_url
        try:
            img_file=urllib.urlopen(image_url)
        except IOError:
            continue
        byte=img_file.read()
        print count,'donwload complete!','-'*10,'size:',byte.__len__()/1024,'KB'
        if(byte.__len__()>7000):
            file_name=image_url.replace('/','_')
            file_name=file_name.replace(':','_')
            end=file_name.__len__()
            if(file_name.rfind('!')!=-1):
                end=file_name.rfind('!')
            if(file_name.rfind('?')!=-1):
                end=file_name.rfind('?')
            file_name=file_name[:end]
            write_file=open(dir_name+'\\'+file_name,'wb')
            write_file.write(byte)
            write_file.close()
            print count,file_name,'complete!'
    driver.quit()
if __name__ == '__main__':
    main()