build(deps): bump uv from 0.8.4 to 0.8.6 in the pip group across 1 directory

gui/main_window.py

@@ -0,0 +1,57 @@
+import sys
+from PySide6.QtWidgets import QApplication, QWidget, QVBoxLayout, QTextEdit, QPushButton
+from PySide6.QtCore import Signal, QObject, QThread
+from scraper.config import index_url
+from .worker import Worker
+
+class EmittingStream(QObject):
+    text_written = Signal(str)
+
+    def write(self, text):
+        self.text_written.emit(str(text))
+
+    def flush(self):
+        pass
+
+class ScraperApp(QWidget):
+    def __init__(self):
+        super().__init__()
+        self.setWindowTitle("Scraper GUI")
+        self.resize(1024, 768)
+
+        self.log = QTextEdit()
+        self.log.setReadOnly(True)
+        btn = QPushButton("Start/Stop scraping")
+
+        layout = QVBoxLayout()
+        layout.addWidget(self.log)
+        layout.addWidget(btn)
+        self.setLayout(layout)
+
+        # redirect print()
+        self.emitter = EmittingStream()
+
+        btn.clicked.connect(self.run_scraping)
+
+    def run_scraping(self):
+
+        # Creation of thread and worker
+        self.thread = QThread()
+        self.worker = Worker(index_url)
+        self.worker.moveToThread(self.thread)
+
+        # Connctions signals
+        self.thread.started.connect(self.worker.run)
+        self.worker.log_signal.connect(self.append_log)
+        self.worker.finished.connect(self.thread.quit)
+
+        self.thread.start()
+
+    def append_log(self, message):
+        self.log.append(message)
+
+if __name__ == "__main__":
+    app = QApplication(sys.argv)
+    window = ScraperApp()
+    window.show()
+    sys.exit(app.exec())

gui/worker.py

@@ -0,0 +1,31 @@
+from PySide6.QtCore import QObject, Signal
+from scraper.scraper import scraper
+
+class Worker(QObject):
+    log_signal = Signal(str)
+    finished = Signal()
+
+    def __init__(self, url):
+        super().__init__()
+        self.url = url
+
+    def run(self):
+        import builtins
+        original_print = builtins.print
+
+        def custom_print(*args, **kwargs):
+            message = " ".join(map(str, args))
+            self.log_signal.emit(message)
+            original_print(*args, **kwargs)
+
+        builtins.print = custom_print
+
+        try:
+            self.log_signal.emit("🚀 Starting scraping...\n")
+            scraper(self.url)
+            self.log_signal.emit("\n✅ Scraping completed.\n")
+        except Exception as e:
+            self.log_signal.emit(f"❌ Error: {str(e)}\n")
+        finally:
+            builtins.print = original_print
+            self.finished.emit()

main.py

@@ -1,4 +1,9 @@
-from scraper.scraper import scraper
-from scraper.config import index_url
+import sys
+from PySide6.QtWidgets import QApplication
+from gui.main_window import ScraperApp
 
-scraper(index_url)
+if __name__ == "__main__":
+    app = QApplication(sys.argv)
+    window = ScraperApp()
+    window.show()
+    sys.exit(app.exec())

scraper/config.py

@@ -11,19 +11,19 @@
 
 # Errors list and path
 exec_errors = []
-errors_path = Path("./data/exec_errors.txt")
+errors_path = Path("../data/exec_errors.txt")
 errors_path.parent.mkdir(parents=True, exist_ok=True)
 
 # Skipped images list and path
 skipped_images = []
-skipped_images_path = Path("./data/skipped_images.txt")
+skipped_images_path = Path("../data/skipped_images.txt")
 skipped_images_path.parent.mkdir(parents=True, exist_ok=True)
 
 # Remove folders and files if exist
-data_dir = Path("./data/images/")
+data_dir = Path("../data/images/")
 if data_dir.exists():
     shutil.rmtree(data_dir)
-print("🧹 Dossier ./data/images/ supprimé.")
+print("🧹 Dossier ../data/images/ supprimé.")
 
 if errors_path.exists():
     os.remove(errors_path)

scraper/extract.py

@@ -2,6 +2,9 @@
 from bs4 import BeautifulSoup
 from urllib.parse import urljoin
 
+def display_book(book):
+    print(f"\n▻ Book \"{book}\" saved\n")
+
 def extract_data(url, errors_log):
     """Function that extracts datas from url.
     The given url represents a product page i.e. a book page
@@ -31,7 +34,9 @@ def extract_data(url, errors_log):
 
     # Extraction of product title
     title = soup.find('li', class_='active').string
-    print(f"  ▷▷ {title} \n")
+
+    display_book(title)
+
     all_datas['title'] = title
 
 

scraper/save.py

@@ -24,7 +24,7 @@ def download_image(url_img, file_path, errors_log, skipped_images):
         directory.mkdir(parents=True, exist_ok=True)
 
         print(f"➥ Image destination : {file_path}")
-        print(f"➥ Path length : {len(str(file_path))}")
+        #print(f"➥ Path length : {len(str(file_path))}")
 
         if not file_path.exists():
             with open(file_path, "wb") as fp:
@@ -34,7 +34,7 @@ def download_image(url_img, file_path, errors_log, skipped_images):
             print(f"⚠️ Image already exists : {file_path}")
             skipped_images.append(file_path)
 
-        print("═════\n")
+        print("="*60+"\n")
 
     except Exception as e:
         print(f"❌ Error for {url_img} → {e}\n")

scraper/scraper.py

@@ -10,21 +10,25 @@ def display_category(cat):
     c = "┈" * int((35 - n) / 2)
     l = "┈" * 60
     print(l)
-    print(c + " PROCESSING CATEGORY ⯈⯈ " + cat + " " + c)
+    print(f"{c} PROCESSING CATEGORY ⯈⯈ \"{cat}\" {c}")
     print(l)
 
-def display_category_end(cat, count):
-    print(f"\n▻ Total books scraped for category {cat} : {count}")
-    print(f"\n▻ Category {cat} saved to {csv_file}\n\n")
+def display_category_end(cat, count, total_count):
+    print(f"\n▻ Total books scraped for category \"{cat}\" : {count} / {total_count}")
+    print(f"\n▻ Category {cat} saved to : {csv_file}\n\n")
     print("─" * 60 + "\n")
 
-
+def display_books_urls(books_list):
+    print("▻▻ List of extracted books urls :\n")
+    for book in books_list:
+        print(f"{book[0]}\n")
+    print("\n")
 
 def scraper(url):
 
     all_categories = get_all_categories(url)
     print(f"All categories extracted from {url}\n")
-
+    total_books_count = 0
     for category in all_categories:
         display_category(category)
 
@@ -39,14 +43,14 @@ def scraper(url):
 
         # Extraction of all pages URL of a category
         book_urls_with_category = extract_books_urls_from_category(url, category)
-        print(f"▻ Extracted urls : {book_urls_with_category}\n")
+        display_books_urls(book_urls_with_category)
 
         book_count = 0
         # Loop for scraping all products url of the category example
         for book_url, cat in book_urls_with_category:
 
             # Extraction of datas from the product page url
-            print("├ Extraction...🚧\n")
+            print("├ Extraction...🚧")
             extracted_datas = extract_data(book_url,exec_errors)
 
             # Transformation of datas
@@ -73,8 +77,8 @@ def scraper(url):
             download_image(image_url, image_path, exec_errors, skipped_images)
 
             book_count += 1
-
-        display_category_end(category, book_count)
+        total_books_count += book_count
+        display_category_end(category, book_count, total_books_count)
 
     # Logging files
     if exec_errors:
@@ -93,4 +97,5 @@ def scraper(url):
 
     else:
         message = "\n\n🙁"
-    print(f"{message} Download completed with {len(exec_errors)} error(s).")
+    print(f"{message} Download completed with {len(exec_errors)} error(s).\n")
+    print(f"Total books scraped : {total_books_count}\n")