🚸 Made output html instead of txt

.gitignore

@@ -2,6 +2,7 @@
 /.vscode
 .DS_Store
 __pycache__
+/output/*
 
 config.ini
 vk_config.v2.json

main.py

@@ -1,4 +1,5 @@
 import configparser
+import argparse 
 import ast
 import sys
 from time import sleep
@@ -17,6 +18,19 @@ if config['SEARCH']['interests'] != "all":
 else:
     interests = "all"
 
+parser = argparse.ArgumentParser(description='Get documents from vk.com')
+parser.add_argument('-a', '--all', action='store_true', 
+    help='Search through all availible documents instead of watching only the most recent uploads.')
+args = parser.parse_args()
+
+def update_status():
+    sys.stdout.write("\033[F")
+    sys.stdout.write("\033[K")
+    sys.stdout.write("\033[F")
+    sys.stdout.write("\033[K")
+    c.print(f'> Documents scanned {photos_processed}')
+    c.print(f'> Documents saved {photos_saved}')
+
 c = Console()
 c.print('[b]Dochunt[/b] starting...', style='yellow')
 vk = authenticate()
@@ -25,7 +39,8 @@ queries = []
 for i in range(len(terms)):
     queries.append({
         'string': terms[i],
-        'last_url': ''
+        'last_url': '',
+        'completed': False
     })
 
 photos_processed = 0
@@ -37,35 +52,35 @@ c.print(f'> Documents saved {photos_saved}')
 while True:
     try:
         for query in queries:
-            response = vk.docs.search(q=query['string'], count=1)
+            if args.all and not query['completed']:
-            image_url = response.popitem()[1][0]['url'] # WTF not readable
+                response = vk.docs.search(q=query['string'], count=1000)
-            image_url_clean = image_url.split('?')[0] # Get url without params
+            else:
+                response = vk.docs.search(q=query['string'], count=1)
+            
+            pics_array = response.popitem()[1]
+            for pic in pics_array:
+                image_url = pic['url'] # WTF not readable
+                image_url_clean = image_url.split('?')[0] # Get url without params
 
-            # If the image we are getting is new do stuff
+                # If the image we are getting is new do stuff
-            if image_url_clean != query['last_url']:
+                if image_url_clean != query['last_url']:
-                photos_processed += 1
+                    photos_processed += 1
-                query['last_url'] = image_url_clean
+                    update_status()
+                    query['last_url'] = image_url_clean
 
-                text = detect(image_url+query['string'])
+                    text = detect(image_url+query['string'])
-                if interests == "all":
+                    if interests == "all":
-                    if not text.isspace():
+                        if not text.isspace():
-                        photos_saved += 1
-                        save_photo(image_url)
-                else:
-                    for interest in interests:
-                        if interest in text:
                             photos_saved += 1
                             save_photo(image_url)
-            
+                    else:
-            sys.stdout.write("\033[F")
+                        for interest in interests:
-            sys.stdout.write("\033[K")
+                            if interest in text:
-            sys.stdout.write("\033[F")
+                                photos_saved += 1
-            sys.stdout.write("\033[K")
+                                save_photo(image_url)
-            c.print(f'> Documents scanned {photos_processed}')
-            c.print(f'> Documents saved {photos_saved}')
 
             sleep(1)
     
     except KeyboardInterrupt:
-        c.print('Goodbye!', style='blue')
+        c.print(' Goodbye!', style='blue')
-        sys.exit()
+        sys.exit()

utils/detect.py

@@ -5,5 +5,9 @@ import requests
 
 def detect(url):
     response = requests.get(url)
-    img = Image.open(io.BytesIO(response.content))
+    try:
+        img = Image.open(io.BytesIO(response.content))
+    except OSError:
+        return ''
+
     return pytesseract.image_to_string(img, lang='rus', timeout=30).lower()

utils/savePhoto.py

@@ -1,8 +1,11 @@
 from rich.console import Console
+import calendar;
+import time;
 c = Console()
+ts = calendar.timegm(time.gmtime())
 
 def save_photo(url):
-    f = open("output.txt", "a", encoding='utf-8')
+    f = open(f"output/{ts}.html", "a", encoding='utf-8')
-    f.write(url)
+    f.write(f'<img width=400 src="{url}"><br>')
     f.close()