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
|
"""
"""
from __future__ import print_function, division
import time
import sys
import pandas as pd
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import random
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=socks5://127.0.0.1:1080')
class Spider(object):
def __init__(self):
self.options = Options()
self.options.add_argument('--headless')
self.driver = webdriver.Chrome(chrome_options=chrome_options,executable_path="chromedriver")
self.driver.implicitly_wait(10)
self.verificationErrors = []
self.accept_next_alert = True
self.url = "https://www.amazon.com/s?ie=UTF8&page=1&rh=n%3A2407749011%2Ck%3AApple&page=1"
self.driver.get(self.url)
self.data = []
self.detail_urls = []
def fanye(self):
next_page_button = self.driver.find_element_by_xpath("//a[@id='pagnNextLink']")
next_page_button.send_keys("\n")
def get_single_page(self):
lists = self.driver.find_elements_by_css_selector("li[id^='result_']")
for li_element in lists[0:20]:
manufacturer, screen_size, product_dimensions_text, rating_content,\
reviews_content, more_offer_text, offer_Price, display_type_text, product_detail = [None] * 9
try:
manufacturer = li_element.find_elements_by_xpath(
".//div[@class='a-fixed-left-grid-col a-col-right']/div/div")[1].text
if "by Apple" not in manufacturer:
continue
except Exception as e:
manufacturer = None
try:
url_detail_in_div = li_element.find_element_by_xpath(
".//div[@class='a-fixed-left-grid-col a-col-right']/div/div/a[contains(@title, 'Apple')]")
detail_url_ = url_detail_in_div.get_attribute("href")
product_detail = url_tile = url_detail_in_div.get_attribute("title")
if "slredirect" in detail_url_:
continue
self.detail_urls.append(detail_url_)
js = 'window.open("{}");'.format(detail_url_)
self.driver.execute_script(js)
handles = self.driver.window_handles
for handle in handles:
if handle != self.driver.current_window_handle:
self.driver.switch_to_window(handle)
break
try:
table1 = self.driver.find_elements_by_xpath("//table[@id='HLCXComparisonTable']/tbody/tr")
for tr in table1:
html1 = tr.get_attribute("innerHTML")
if "Screen Size" in html1:
td_inches = tr.find_elements_by_xpath(".//td")[0]
screen_size = td_inches.text
break
except Exception as e:
pass
try:
table2 = self.driver.find_elements_by_xpath("//table[@id='productDetails_detailBullets_sections1']/tbody/tr")
for tr in table2:
html2 = tr.get_attribute("innerHTML")
if "Product Dimensions" in html2:
product_dimensions_html = tr.find_elements_by_xpath(".//td")[0]
product_dimensions_text = product_dimensions_html.text
continue
if "Customer Reviews" in html2:
rating_html = tr.find_element_by_xpath(".//td")
rating_text = rating_html.text
reviews_text, rating_content = rating_text.split("\n")
reviews_content = reviews_text.split(" ")[0]
continue
except Exception as e:
pass
self.driver.close()
self.driver.switch_to_window(handles[0])
except Exception as e:
pass
try:
more_offer_html = li_element.find_element_by_css_selector("a[href*='offer-listing']")
more_offer_text = more_offer_html.text
except Exception as e:
pass
try:
offer_price_html = li_element.find_element_by_xpath(".//span[@class='sx-price sx-price-large']")
offer_Price = offer_price_html.text
except Exception as e:
pass
try:
display_type_html = li_element.find_elements_by_xpath(
".//dl[@class='a-definition-list a-vertical s-padding-left-base']/li/span[@class='a-list-item a-size-small a-color-secondary']")
for _span in display_type_html:
if "Display Type:" in _span.text:
display_type_html = _span.text
display_type_text = display_type_html.split(":")[1]
break
except Exception as e:
pass
_tmp_dt = [manufacturer, screen_size, product_dimensions_text, rating_content, reviews_content, more_offer_text,
offer_Price, display_type_text, product_detail, None, None]
print(_tmp_dt)
self.data.append(_tmp_dt)
time.sleep(random.randint(0,2))
def main(self):
i=0
while True and i<=4:
self.get_single_page()
try:
i=i+1
self.fanye()
except:
break
return self.data,self.detail_urls
a = Spider()
dt, url_lists = a.main()
print(url_lists)
col_name = ["Manufacturer", "Display_Size", "Display_Dimensions", "Rating", "Number_of_Review", "More_Offer", "Offer_Price", "Display_Type", "Product_detail", "Special_Feature", "Special_Offer"]
df = pd.DataFrame(dt,columns=col_name)
print(df)
|