File size: 5,782 Bytes
f4d52c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import time
import urllib.request
import os
import re
from random import randint
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from commands.driver_instance import create_url_headers, tab_handler
from commands.exec_path import imgList
from commands.universal import searchQuery, save_Search, continue_Search, contains_works
from ai.classifying_ai import img_classifier


def getOrderedYandexImages(
    driver, exec_path, user_search, num_pics, filters, imageOrientation):
    global image_locations, image_names, ai_mode
    image_names = imgList(mode=2)
    ai_mode = True
    recents = True if 1 in filters else False

    image_locations = []
    link = "https://yandex.com/images/search?isize=large&"
    link = link + "text=" + user_search.replace(" ", "+").replace("_", "+")
    if imageOrientation:
        orientations = ["horizontal", "vertical", "square"]
        link += f"&iorient={orientations[imageOrientation]}"
    driver.get(link)

    WebDriverWait(driver, timeout=11).until(
        EC.presence_of_element_located((By.XPATH, '//*[@class="SerpList"]'))
    )

    driver.find_element(
        By.XPATH,
        "//*[@class='SimpleImage SimpleImage_showPlaceholderIcon SerpItem-Thumb']//a",
    ).click()

    grid_search(driver, num_pics, exec_path, user_search)

    time.sleep(20)
    driver.close()

    return image_locations


def grid_search(driver, num_pics, exec_path, user_search):
    WebDriverWait(driver, timeout=11).until(
        EC.presence_of_element_located(
            (By.XPATH, "//*[contains(@class, 'MMGallery-Item')]")
        )
    )
    images = driver.find_elements(By.XPATH, "//*[@class='MMGallery-Container']/*")

    for image in images:
        time.sleep(2)
        # Navigate the webpage and filter the image link 
        try:
            if len(image_locations) >= num_pics:
                break

            driver.execute_script("arguments[0].click();", image)
            time.sleep(0.5)
            imageLink = driver.find_element(
                By.XPATH,
                '//*[@class="OpenImageButton OpenImageButton_text OpenImageButton_sizes MMViewerButtons-OpenImageSizes"]//a',
            ).get_attribute("href")

            if (imageLink.rsplit("/",1)[-1].encode("ascii", "ignore")
                .decode("ascii")) in image_names:
                print("Image already exists, moving to another image...\n")
                continue
        except:
            print("I ran into an error finding the image, closing the tab and moving on...\n")
            time.sleep(randint(0, 1) + randint(0, 9) / 10)
            continue
        
        # Ai mode check
        try:
            if ai_mode:
                checker = ai_dl(image, exec_path, driver, user_search)
                if checker:
                    continue
        except Exception as e: # TODO: Implement proper exception handling in case of http error 404
            time.sleep(randint(0, 1) + randint(0, 9) / 10)
            checker = ai_dl(image, exec_path, driver, user_search, site="https://yandex.com/")
        except:
            time.sleep(randint(0, 1) + randint(0, 9) / 10)
            print("AI mode failed to check the image, skipping...\n")
            continue
        
        # Download the image
        try:
            download_image(
                exec_path=exec_path,
                driver=driver,
                image=imageLink,
                user_search=user_search,
            )
        except: # TODO: Use the same exception handling as above to try and redownload the image
            print("I ran into an error downloading, closing the tab and moving on...\n")
            time.sleep(randint(0, 1) + randint(0, 9) / 10)


def download_image(exec_path, driver, image, user_search, mode=1, site=0):
    tempDLAttr = image
    matching = re.search(r"([^/]+\.(?:jpg|jpeg|png|webp))", image.rsplit("/", 1)[-1])

    if not matching:
        tempDLAttr += ".png"
    if tempDLAttr.startswith('//'):
        tempDLAttr = 'https:' + tempDLAttr

    tempDLName = (
    re.search(r"([^/]+\.(?:jpg|jpeg|png|webp))", tempDLAttr.rsplit("/", 1)[-1])
    .group(1)
    .encode("ascii", "ignore")
    .decode("ascii"))
    
    if not mode:
        tempDLName = re.sub(r'[\\/*?:"<>|]', "", tempDLName)
    img_loc = f"./{exec_path.folder_path}/{tempDLName}"
    
    # User other site headers (to be implemented properly)
    if site:
        urllib.request.install_opener(create_url_headers(tempDLAttr, site=site))
        urllib.request.urlretrieve(tempDLAttr, img_loc)

    urllib.request.install_opener(create_url_headers(tempDLAttr))
    urllib.request.urlretrieve(tempDLAttr, img_loc)

    if mode:
        print(f"{tempDLAttr}\n")
        image_locations.append(img_loc)
        image_names.append(f"{tempDLName.split('.')[0]}")
    return img_loc


def ai_dl(image, exec_path, driver, user_search, site=""):
    checker = 0
    image_thumbnail = image.find_element(
        By.XPATH, './/*[@class="MMThumbImage-Image"]'
    ).get_attribute("style")

    # Filter url from the style attribute
    image_thumbnail = re.findall(r'url\("(.+?)"\)', image_thumbnail)[0]

    # Download the image thumbnail
    image_loc = download_image(
        exec_path=exec_path,
        driver=driver,
        image=image_thumbnail,
        user_search=user_search,
        mode=0,
        site=site
    )

    # Check if the image is good or not and delete the image
    if img_classifier(image_loc):
        print("AI Mode: I approve this image")
    else:
        print("AI Mode: Skipping this image\n")
        checker = 1
    os.remove(image_loc)
    return checker