redesign get images to work from tba, accepts imgur and insta

image_errors.txt

@@ -0,0 +1,10 @@
+(1014, IndexError('list index out of range'))
+(1622, IndexError('list index out of range'))
+(2485, IndexError('list index out of range'))
+(4159, IndexError('list index out of range'))
+(6988, IndexError('list index out of range'))
+(7848, IndexError('list index out of range'))
+(8513, IndexError('list index out of range'))
+(9008, IndexError('list index out of range'))
+(9416, IndexError('list index out of range'))
+(9787, IndexError('list index out of range'))

scoutingapp/src/getImages.py → scoutingapp/src/getImagesTBA.py

@@ -1,20 +1,21 @@
 import os
 import time
 import requests
-import bs4
 
 TBA_API_KEY = r''
 IMGUR_CLIENT_ID = r''
 IMGUR_ETAG = r''
-EVENT_KEY = ''
+EVENT_KEY = r''
 
 if not (TBA_API_KEY and IMGUR_CLIENT_ID and IMGUR_ETAG and EVENT_KEY):
     raise PermissionError("Some keys are missing! Go into code and insert your keys.")
 
-FOLDER_PATH = './components/img'
+FOLDER_PATH = './src/components/img'
 
 # Headers for the API request
 TBA_HEADERS = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:128.0) Gecko/20100101 Firefox/128.0',
+    'Referer': 'https://www.thebluealliance.com/',
     'X-TBA-Auth-Key': TBA_API_KEY
 }
 
@@ -40,7 +41,7 @@ def fetch_teams(event_key) -> list[int]:
     return sorted([team['team_number'] for team in response.json()])
 
 
-def scrape_robot_image(team_number: int) -> None | str:
+def scrape_robot_image(team_number: int) -> str:
     """
     Returns the url of the location of the robot image used on TBA.
     This function fails (raises TypeError or returns None) when there is no robot image found on TBA.
@@ -49,38 +50,40 @@ def scrape_robot_image(team_number: int) -> None | str:
     :returns: The url of the image
     """
 
-    url = f"https://www.thebluealliance.com/team/{team_number}"
+    url = f'https://www.thebluealliance.com/api/v3/team/frc{team_number}/media/2024'
     response = requests.get(url, headers=TBA_HEADERS)
-
-    if response.status_code != 200:
-        print(f"{response.status_code}: Failed to retrieve page for team {team_number}")
-        return
-
-    soup = bs4.BeautifulSoup(response.text, 'html.parser')
-    # Find the image by its class name or id. This may change, so inspect the page to find the correct identifier.
-    image_tag = soup.find('a', {'class': 'gallery'})
-    image_url = image_tag['href']
-
-    return image_url
+    response.raise_for_status()
+    data = [x for x in response.json() if x['type'] not in ['avatar', 'youtube']]
+    return data[0]['direct_url']
 
 
-def download_image(team_number: int, image_url: str) -> None:
+def download_image(team_number: int, image_url: str, image_host: str) -> None:
     """
     Downloads the image from the given url to the appropirate place in code.
     Will download to scoutingapp/src/components/img and will download as team_number.jpeg.
 
     :param team_number: The team number for the robot
     :param image_url: The url location of the image that needs to be downloaded
+    :param image_host: Website hosting image (instagram | imgur)
     :returns: None
     """
 
-    image_hash = image_url.split("/")[3].removesuffix(".jpg").removesuffix(".jpeg").removesuffix(".png")
-    image_ending = image_url.split(".")[-1]
-    image_ending = "jpeg" if image_ending == "jpg" else image_ending
+    if image_host == "imgur":
+        image_hash = image_url.split("/")[3].removesuffix(".jpg").removesuffix(".jpeg").removesuffix(".png")
+        image_ending = image_url.split(".")[-1]
+        image_ending = "jpeg" if image_ending == "jpg" else image_ending
+
+        image_url = f'https://i.imgur.com/{image_hash}.{image_ending}'
 
-    image_url = f'https://i.imgur.com/{image_hash}.{image_ending}'
+        image_response = requests.get(image_url, headers=IMGUR_HEADERS)
+    elif image_host == "instagram":
+        image_url = f'https://thebluealliance.com/{image_url}'
+        image_ending = "jpeg"
+
+        image_response = requests.get(image_url, headers=TBA_HEADERS)
+    else:
+        return
 
-    image_response = requests.get(image_url, headers=IMGUR_HEADERS)
     image_response.raise_for_status()
 
     file_path = os.path.join(FOLDER_PATH, f"{team_number}.{image_ending}")
@@ -108,7 +111,7 @@ def main(teams: tuple[int] = ()) -> None:
     failed_teams = {}
     for team in teams:
         print(f'{team}: Starting...')
-        time.sleep(0.5)
+        time.sleep(2)
 
         try:
             url = scrape_robot_image(team)
@@ -118,14 +121,16 @@ def main(teams: tuple[int] = ()) -> None:
                 print(f"{team}: Failed to retrieve image link.")
                 failed_teams[team] = "Failed to retrieve image link."
                 continue
-            if "imgur" not in url:
-                print(f"{team}: Image is not imgur.")
-                failed_teams[team] = "Image is not imgur."
-                continue
+            if "imgur" in url:
+                download_image(team, url, "imgur")
+            elif "instagram" in url:
+                download_image(team, url, "instagram")
+            else:
+                print(f"{team}: Image host not recognized.")
+                failed_teams[team] = "Image host not recognized."
 
-            download_image(team, url)
             print(f'{team}: Success.')
-        except TypeError:
+        except (TypeError, IndexError):
             print(f"{team}: Image not found.")
             failed_teams[team] = "Image not found."
         except Exception as e:
@@ -138,7 +143,7 @@ def main(teams: tuple[int] = ()) -> None:
     print("NOTE: Some teams did not run properly.")
     print(*failed_teams.items(), sep="\n")
 
-    with open("image_errors.txt", 'w') as err_file:
+    with open("./src/image_errors.txt", 'w') as err_file:
         for fail in failed_teams.items():
             err_file.write(str(fail) + "\n")
 

scoutingapp/src/image_errors.txt

@@ -1,18 +0,0 @@
-(365, 'Image is not imgur.')
-(1014, 'Image not found.')
-(1279, 'Image is not imgur.')
-(1622, 'Image not found.')
-(2472, 'Image is not imgur.')
-(2485, 'Image not found.')
-(3654, 'Image is not imgur.')
-(4159, 'Image not found.')
-(5002, 'Image is not imgur.')
-(5987, 'Image is not imgur.')
-(6988, 'Image not found.')
-(7848, 'Image not found.')
-(8513, 'Image not found.')
-(8727, 'Image is not imgur.')
-(9008, 'Image not found.')
-(9416, 'Image not found.')
-(9564, 'Image is not imgur.')
-(9787, 'Image not found.')