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
| # 필요 라이브러리 임포트
import time
import urllib.request
import os
from random import randrange
from stem import Signal
from stem.control import Controller
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.firefox.options import Options
from urllib.parse import quote_plus
def function_check(test_url: str) -> None:
# tor browser 의 기능 동작 체크
with Controller.from_port(port=9051) as controller:
while True:
url = test_url
hostname = "socks5://127.0.0.1"
port = "9050"
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument(f"--proxy-server={hostname + ':' + port}")
driver = webdriver.Chrome(options=chrome_options)
driver.get(url)
time.sleep(20)
driver.quit()
controller.authenticate("password for tor browser")
controller.signal(Signal.NEWNYM)
if controller.is_newnym_available() == False:
print(f"waiting for Tor to Change IP: {controller.get_newnym_wait()} sec")
time.sleep(controller.get_newnym_wait())
# 크롤러 클래스 정의
class Crawler:
def __init__(self, url: str, query: str, max_images: int=None) -> None:
self.__mode = "google" if "google" in url else "naver"
self.__url = url if self.__mode == "google" else url + quote_plus(query)
self.__query = query
self.__max_images = max_images
options = Options()
options.set_preference("network.proxy.type", 1)
options.set_preference("network.proxy.socks", "127.0.0.1")
options.set_preference("network.proxy.socks_port", 9050)
opener = urllib.request.build_opner()
opener.addheaders = [('Users-Agents', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
urllib.request.install_opener(opener)
self.driver = webdriver.Firefox(options=options)
self.driver.get("http://icanhazip.com/") # 단순 ip 확인용 웹사이트
current_ip = self.driver.page_source.split("<pre>")[-1].split("\n")[0] # 현재 접속 IP
# 현재 접속 IP 와 본래의 IP 와 일치한다면 바로 종료
if current_ip == "###.###.###.###":
logger.error(f"changed ip is same as original ip (###.###.###.### == {current_ip})")
return
self.new_tab()
def new_tab(self) -> None:
# ip 확인용 사이트가 아닌 실제 크롤링을 실시할 탭 열기
tab = self.driver.find_element(By.TAG_NAME, "body")
tab.send_keys(Keys.CONTROL + "t")
self.driver.get(self.__url)
# 접속 IP 가 바뀌게 되면 뭔가를 Accept 하라는 창이 뜨는데 해당 창의 Accept 태그
try:
self.driver.find_element(By.ID, "L2AGLb").click()
except:
pass
def search_image(self) -> None:
# google 의 경우 검색창에 크롤링 할 검색어 입력 후 처리
search_bar = self.driver.find_element(By.NAME, "q")
search_bar.send_keys(self.__query)
search_bar.submit()
def load_image(self) -> None:
# 검색 된 이미지 전체 로드
last_height = self.driver.execute("return document.body.scrollHeight;")
while True:
# 아래로 스크롤
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(randrange(10, 14)) # 페이지가 로드 될 때까지 기다림
new_height = self.driver.execute_script("return document.body.scrollHeight;")
if new_height == last_height:
try:
# 일정수준 이미지가 로드 되면 show more image 등이 뜨며 클릭버튼이 생기는데 해당 버튼을 클릭해 추가 이미지들을 로드
more_images = self.driver.find_element(By.CSS_SELECTOR, ".mye4qd")
more_images.click()
except:
break
last_height = new_height
def get_images_google(self) -> None:
# google 에서 크롤링 할 때
time.sleep(randrange(10, 15))
images = self.driver.find_elements(By.CSS_SELECTOR, ".rg_i")
for idx, img in enumerate(images[:self.__max_images]):
try:
img.click()
time.sleep(randrange(7, 10))
logger.info(f"{idx} / {len(images)}")
img_url = self.driver.find_element(By.XPATH, "/html/body/div[2]/c-wiz/div[3]/div[2]/div[3]/div[2]/div[2]/div[2]/div[2]/c-wiz/div/div/div/div[3]/div[1]/a/img[1]").get_attribute("src")
urllib.request.urlretrieve(img_url, f"image/{time.time()}.jpg")
except Exception as e:
logger.error(e)
pass
def get_images_naver(self) -> None:
# naver 에서 크롤링 할 때
time.sleep(randrange(10, 14))
images = self.driver.find_elements(By.CLASS_NAME, "_image")
for idx, img in enumerate(images[:self.__max_images]):
try:
img.click()
time.sleep(randrange(3, 7))
logger.info(f"{idx} / {len(images)}")
img_url = self.driver.find_element(By.XPATH, '//*[@id="main_pack"]/section[2]/div/div[2]/div/div/div[1]/div[1]/div/div/div[1]/div[1]/img').get_attribute("src")
urllib.request.urlretrieve(img_url, f"images/{time.time()}.jpg")
except Exception as e:
logger.error(e)
pass
def run(self) -> None:
os.makedirs("images", exist_ok=True)
if self.__mode == "google":
self.search_image()
self.load_image()
self.get_images_google()
else:
self.load_image()
self.get_images_naver()
def __del__(self) -> None:
self.driver.quit()
if __name__ == "__main__":
google = Crawler("https://www.google.com/imghp?hl=en&tab=ri&authuser=0&ogbl", "과자 유통기한", 100)
google.run()
naver = Crawler("https://search.naver.com/search.naver?where=image§ion=image&query=", "과자 유통기한", 100)
naver.run()
|
