forked from Mactarvish/AutoCrawler
-
Notifications
You must be signed in to change notification settings - Fork 0
/
collect_links.py
398 lines (293 loc) · 14.5 KB
/
collect_links.py
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
"""
Copyright 2018 YoongiKim
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.common.exceptions import ElementNotVisibleException, StaleElementReferenceException
import platform
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
import os.path as osp
class CollectLinks:
def __init__(self, no_gui=False, proxy=None):
executable = ''
if platform.system() == 'Windows':
print('Detected OS : Windows')
executable = './chromedriver/chromedriver_win.exe'
elif platform.system() == 'Linux':
print('Detected OS : Linux')
executable = './chromedriver/chromedriver_linux'
elif platform.system() == 'Darwin':
print('Detected OS : Mac')
executable = './chromedriver/chromedriver_mac'
else:
raise OSError('Unknown OS Type')
if not osp.exists(executable):
raise FileNotFoundError('Chromedriver file should be placed at {}'.format(executable))
chrome_options = Options()
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
if no_gui:
chrome_options.add_argument('--headless')
if proxy:
chrome_options.add_argument("--proxy-server={}".format(proxy))
self.browser = webdriver.Chrome(ChromeDriverManager().install(), chrome_options=chrome_options)
browser_version = 'Failed to detect version'
chromedriver_version = 'Failed to detect version'
major_version_different = False
if 'browserVersion' in self.browser.capabilities:
browser_version = str(self.browser.capabilities['browserVersion'])
if 'chrome' in self.browser.capabilities:
if 'chromedriverVersion' in self.browser.capabilities['chrome']:
chromedriver_version = str(self.browser.capabilities['chrome']['chromedriverVersion']).split(' ')[0]
if browser_version.split('.')[0] != chromedriver_version.split('.')[0]:
major_version_different = True
print('_________________________________')
print('Current web-browser version:\t{}'.format(browser_version))
print('Current chrome-driver version:\t{}'.format(chromedriver_version))
if major_version_different:
print('warning: Version different')
print(
'Download correct version at "http://chromedriver.chromium.org/downloads" and place in "./chromedriver"')
print('_________________________________')
def get_scroll(self):
pos = self.browser.execute_script("return window.pageYOffset;")
return pos
def wait_and_click(self, xpath):
# Sometimes click fails unreasonably. So tries to click at all cost.
try:
w = WebDriverWait(self.browser, 15)
elem = w.until(EC.element_to_be_clickable((By.XPATH, xpath)))
elem.click()
self.highlight(elem)
except Exception as e:
print('Click time out - {}'.format(xpath))
print('Refreshing browser...')
self.browser.refresh()
time.sleep(2)
return self.wait_and_click(xpath)
return elem
def highlight(self, element):
self.browser.execute_script("arguments[0].setAttribute('style', arguments[1]);", element,
"background: yellow; border: 2px solid red;")
@staticmethod
def remove_duplicates(_list):
return list(dict.fromkeys(_list))
def google(self, keyword, add_url=""):
self.browser.get("https://www.google.com/search?q={}&source=lnms&tbm=isch{}".format(keyword, add_url))
time.sleep(1)
print('Scrolling down')
elem = self.browser.find_element(By.TAG_NAME, "body")
for i in range(60):
elem.send_keys(Keys.PAGE_DOWN)
time.sleep(0.2)
try:
# You may need to change this. Because google image changes rapidly.
# btn_more = self.browser.find_element(By.XPATH, '//input[@value="결과 더보기"]')
# self.wait_and_click('//input[@id="smb"]')
self.wait_and_click('//input[@type="button"]')
for i in range(60):
elem.send_keys(Keys.PAGE_DOWN)
time.sleep(0.2)
except ElementNotVisibleException:
pass
photo_grid_boxes = self.browser.find_elements(By.XPATH, '//div[@class="isv-r PNCib MSM1fd BUooTd"]')
print('Scraping links')
links = []
for idx, box in enumerate(photo_grid_boxes):
# print('Scraping', idx)
try:
imgs = box.find_elements(By.TAG_NAME, 'img')
for img in imgs:
# self.highlight(img)
src = img.get_attribute("src")
# Google seems to preload 20 images as base64
if str(src).startswith('data:'):
src = img.get_attribute("data-iurl")
links.append(src)
except Exception as e:
print('[Exception occurred while collecting links from google] {}'.format(e))
links = self.remove_duplicates(links)
print('Collect links done. Site: {}, Keyword: {}, Total: {}'.format('google', keyword, len(links)))
self.browser.close()
return links
def naver(self, keyword, add_url=""):
self.browser.get(
"https://search.naver.com/search.naver?where=image&sm=tab_jum&query={}{}".format(keyword, add_url))
time.sleep(1)
print('Scrolling down')
elem = self.browser.find_element(By.TAG_NAME, "body")
for i in range(60):
elem.send_keys(Keys.PAGE_DOWN)
time.sleep(0.2)
imgs = self.browser.find_elements(By.XPATH,
'//div[@class="photo_bx api_ani_send _photoBox"]//img[@class="_image _listImage"]')
print('Scraping links')
links = []
for img in imgs:
try:
src = img.get_attribute("src")
if src[0] != 'd':
links.append(src)
except Exception as e:
print('[Exception occurred while collecting links from naver] {}'.format(e))
links = self.remove_duplicates(links)
print('Collect links done. Site: {}, Keyword: {}, Total: {}'.format('naver', keyword, len(links)))
self.browser.close()
return links
def google_full(self, keyword, add_url="", limit=100):
print('[Full Resolution Mode]')
self.browser.get("https://www.google.com/search?q={}&tbm=isch{}".format(keyword, add_url))
time.sleep(1)
elem = self.browser.find_element(By.TAG_NAME, "body")
print('Scraping links')
self.wait_and_click('//div[@data-ri="0"]')
time.sleep(1)
links = []
limit = 10000 if limit == 0 else limit
count = 1
last_scroll = 0
scroll_patience = 0
NUM_MAX_SCROLL_PATIENCE = 100
while len(links) < limit:
try:
xpath = '//div[@class="n4hgof"]//img[@class="r48jcc pT0Scc iPVvYb"]'
imgs = elem.find_elements(By.XPATH, xpath)
for img in imgs:
self.highlight(img)
src = img.get_attribute('src')
if src is not None and src not in links:
links.append(src)
print('%d: %s' % (count, src))
count += 1
except KeyboardInterrupt:
break
except StaleElementReferenceException:
# print('[Expected Exception - StaleElementReferenceException]')
pass
except Exception as e:
print('[Exception occurred while collecting links from google_full] {}'.format(e))
scroll = self.get_scroll()
if scroll == last_scroll:
scroll_patience += 1
else:
scroll_patience = 0
last_scroll = scroll
if scroll_patience >= NUM_MAX_SCROLL_PATIENCE:
break
elem.send_keys(Keys.RIGHT)
links = self.remove_duplicates(links)
print('Collect links done. Site: {}, Keyword: {}, Total: {}'.format('google_full', keyword, len(links)))
self.browser.close()
return links
def naver_full(self, keyword, add_url=""):
print('[Full Resolution Mode]')
self.browser.get(
"https://search.naver.com/search.naver?where=image&sm=tab_jum&query={}{}".format(keyword, add_url))
time.sleep(1)
elem = self.browser.find_element(By.TAG_NAME, "body")
print('Scraping links')
self.wait_and_click('//div[@class="photo_bx api_ani_send _photoBox"]')
time.sleep(1)
links = []
count = 1
last_scroll = 0
scroll_patience = 0
while True:
try:
xpath = '//div[@class="image _imageBox"]/img[@class="_image"]'
imgs = self.browser.find_elements(By.XPATH, xpath)
for img in imgs:
self.highlight(img)
src = img.get_attribute('src')
if src not in links and src is not None:
links.append(src)
print('%d: %s' % (count, src))
count += 1
except StaleElementReferenceException:
# print('[Expected Exception - StaleElementReferenceException]')
pass
except Exception as e:
print('[Exception occurred while collecting links from naver_full] {}'.format(e))
scroll = self.get_scroll()
if scroll == last_scroll:
scroll_patience += 1
else:
scroll_patience = 0
last_scroll = scroll
if scroll_patience >= 100:
break
elem.send_keys(Keys.RIGHT)
elem.send_keys(Keys.PAGE_DOWN)
links = self.remove_duplicates(links)
print('Collect links done. Site: {}, Keyword: {}, Total: {}'.format('naver_full', keyword, len(links)))
self.browser.close()
return links
def baidu_full(self, keyword, add_url="", limit=100):
print('[Full Resolution Mode]')
url = r"https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1687882242293_R&pv=&ic=&nc=1&z=&hd=&latest=©right=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&dyTabStr=MCwxLDYsMyw0LDUsMiw4LDcsOQ%3D%3D&ie=utf-8&sid=&word=" + keyword
url = r"https://image.baidu.com/search/detail?ct=503316480&z=&tn=baiduimagedetail&ipn=d&word=flower&step_word=&ie=utf-8&in=&cl=2&lm=-1&st=-1&hd=&latest=©right=&cs=4174763854,3212615574&os=292657261,4258505619&simid=65710209,733330822&pn=0&rn=1&di=7214885350303334401&ln=1782&fr=&fmq=1687882242293_R&fm=result&ic=&s=undefined&se=&sme=&tab=0&width=&height=&face=undefined&is=0,0&istype=2&ist=&jit=&bdtype=0&spn=0&pi=0&gsm=1e&objurl=https%3A%2F%2Fallpicts.in%2Fdownload%2F24154%2FMacro_Photography_Wallpaper_of_White_Flower_and_Dark_Background.jpg&rpstart=0&rpnum=0&adpicid=0&nojc=undefined&dyTabStr=MCwxLDYsMyw0LDUsMiw4LDcsOQ%3D%3D&ctd=1687886409089^3_1200X707%1"
self.browser.get(url)
time.sleep(1)
print('Scraping links')
# self.wait_and_click('//li[@pn="0"]')
# time.sleep(1)
elem = self.browser.find_element(By.TAG_NAME, "body")
elem.send_keys(Keys.PAGE_DOWN)
elem.send_keys(Keys.RIGHT)
links = []
limit = 10000 if limit == 0 else limit
count = 1
last_scroll = 0
scroll_patience = 0
NUM_MAX_SCROLL_PATIENCE = 100
while len(links) < limit:
try:
xpath = '//div[@class="img-wrapper"]//img[@class="currentImg"]'
imgs = elem.find_elements(By.XPATH, xpath)
for img in imgs:
self.highlight(img)
src = img.get_attribute('src')
if src is not None and src not in links:
links.append(src)
print('%d: %s' % (count, src))
count += 1
except KeyboardInterrupt:
break
except StaleElementReferenceException:
# print('[Expected Exception - StaleElementReferenceException]')
pass
except Exception as e:
print('[Exception occurred while collecting links from baidu_full] {}'.format(e))
# scroll = self.get_scroll()
# print("---", scroll)
# if scroll == last_scroll:
# scroll_patience += 1
# else:
# scroll_patience = 0
# last_scroll = scroll
# if scroll_patience >= NUM_MAX_SCROLL_PATIENCE:
# break
print("----", "sending right")
elem.send_keys(Keys.RIGHT)
links = self.remove_duplicates(links)
print('Collect links done. Site: {}, Keyword: {}, Total: {}'.format('baidu_full', keyword, len(links)))
self.browser.close()
return links
if __name__ == '__main__':
collect = CollectLinks()
links = collect.baidu_full('flower')
print(len(links), links)