Sat, Aug 3, 2024, 9:50 AM +03:00

database_updater.py

@@ -1,5 +1,6 @@
 import sqlite3
 import scrapper
+import images_scrapper
 
 con = sqlite3.connect('db\database.db')
 
@@ -11,6 +12,8 @@
 
 titles, engines = scrapper()
 
+images = images_scrapper()
+
 # Creating table
 table = """ CREATE TABLE rocket_engines (Id INTEGER NOT NULL PRIMARY KEY, """
 for i in range(len(titles)):
@@ -20,7 +23,7 @@
     elif type(engines[17][i]) == float:
         table += """ REAL, """
 table = table.removesuffix(""", """)
-table += """); """
+table += """Image TEXT); """
 cur.execute(table)
 
 print("Table is Ready")

images_scrapper.py

@@ -31,6 +31,7 @@ def images_scrapper():
     engines = scrapper()[1]
     paths = ()
     for engine in engines:
+        path = ""
         engine_name = engine[0]
         goog_search = "https://www.google.com/search?sclient=psy-ab&client=ubuntu&hs=k5b&channel=fs&biw=1366&bih=648&noj=1&q=" + engine_name.replace(" ", "+") + "+rocket+engine+wikipedia"
 
@@ -52,8 +53,9 @@ def images_scrapper():
                     if soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset"):
                         if len(soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset").split()) > 2 and "Aeon" not in engine_name:
                             pic_url = "https:" + str(soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset").split()[2])
-                            download_image(pic_url, f"./images/{engine_name}.jpg")
-                            paths += f"./images/{engine_name}.jpg"
+                            path = f"./images/{engine_name}.jpg"
+                            download_image(pic_url, path)
+        paths += path
     return paths
 
 sys.modules[__name__] = images_scrapper