.gitea/workflows/build.yaml

@@ -1,39 +0,0 @@
-name: Actions Build Docker Image
-run-name: ${{ gitea.actor }} is building new image 🚀
-on: [push]
-
-jobs:
-  Explore-Gitea-Actions:
-    runs-on: soaska
-    steps:
-      - run: echo "🎉 The job was automatically triggered by a ${{ gitea.event_name }} event."
-      - name: Install Node.js
-        run: |
-          apk add --no-cache nodejs          
-      - name: Check out repository code
-        uses: actions/checkout@v3
-      - name: List files in the repository
-        run: |
-          ls ${{ gitea.workspace }}                    
-      - run: echo "🍏 This job's status is ${{ job.status }}."
-      - name: Install Docker
-        run: |
-          apk add --no-cache docker          
-      - name: Start Docker service
-        run: |
-          dockerd &
-          sleep 5
-          docker info                    
-      - name: Build Dockerfile
-        run: |
-          docker build -t $(basename ${{ github.repository }}) .        
-      - name: Upload Docker image to soaska.ru
-        run: |
-          package_name=$(basename ${{ github.repository }})
-          branch_name=$(git rev-parse --abbrev-ref HEAD)
-
-          docker login -u ${{ secrets.username }} -p ${{ secrets.password }} soaska.ru
-          docker tag $package_name soaska.ru/soaska/$package_name:$branch_name
-          docker tag $package_name soaska.ru/soaska/$package_name:latest
-          docker push soaska.ru/soaska/$package_name:$branch_name
-          docker push soaska.ru/soaska/$package_name:latest

.gitignore

@@ -4,7 +4,4 @@
 /.idea
 /__pycache__
 /logfile.log
-/data
+/data
-
-# Временно
-/docker

Dockerfile

@@ -1,11 +1,15 @@
 FROM python:3.11-slim-bullseye
 
 WORKDIR /app/
+
 COPY requirements.txt .
+
 RUN pip install -r requirements.txt --no-cache-dir
+
 RUN playwright install chromium
+
 RUN playwright install-deps
 
 COPY . .
-ENTRYPOINT ["python", "main.py"]
+
-CMD [ "start" ]
+CMD ["python", "main.py"]

README.md

@@ -14,8 +14,8 @@ cd eljur
 ```
 
 #### Создание .env файла
-Используйте [sample.env](https://git.soaska.ru/sosiska/eljur/-/blob/main/sample.env?ref_type=heads), чтобы создать свой .env файл.
+Используйте sample.env, чтобы создать свой .env файл.
-[env.example](https://git.soaska.ru/sosiska/eljur/-/blob/main/env.example?ref_type=heads) - пример, как может выглядеть файл .env
+env.example - пример, как может выглядеть файл .env
 
 ```
 ELJUR_LOGIN=Vasya2005

main.py

@@ -39,7 +39,7 @@ def update_html(val=""):
         update_html(val=val)
     except:
         logging.critical(f"cant update data/table.html: {Exception}")
-        exit(1) 
+        exit(1)
 
 
 def get_html():
@@ -48,8 +48,8 @@ def get_html():
         with open('data/table.html') as html_file:
             val = html_file.read()
         logging.debug("data/table.html got")
-    except Exception as error:
+    except:
-        logging.error(f"cant read data/table.html: {str(error)}")
+        logging.error(f"cant read data/table.html: {Exception}")
     return val
 
 
@@ -78,7 +78,6 @@ def verify_data():
  
 
 def run():
-    global new_table, old_table
     new_table = scrape()
     old_table = get_html()
     old_last_block = ""
@@ -96,19 +95,14 @@ def run():
             
             update_html(new_table)
             new_table_soup = BeautifulSoup(new_table, "lxml")
-            new_table_pretty = new_table_soup.prettify()
+            new_table = new_table_soup.prettify()
             old_table_soup = BeautifulSoup(old_table, "lxml")
-            old_table_pretty = old_table_soup.prettify()
+            old_table = old_table_soup.prettify()
-            get_difference(old_table_pretty, new_table_pretty)
+            get_difference(old_table, new_table)
 
 
             if old_last_block != new_last_block:
                 send_photo("data/screenshot.png")
-            else:
-                send_photo("sad.png")
-            
-            send_document("data/difference.html")
-            send_document("data/table.html")
 
             return
     logging.debug("same result. nothing to do")

scraper.py

@@ -6,22 +6,24 @@ from playwright._impl import _api_types
 from os import mkdir
 
 
-# Use sync version of Playwright
-p = sync_playwright().start()
-# Launch the browser
-browser = p.chromium.launch()
-logging.debug("browser opened")
-
-# Open a new browser page
-page = browser.new_page()
-
-
 def scrape():
-    global page
+    # Use sync version of Playwright
-    try:
+
-        # Open our test file in the opened page
+    with sync_playwright() as p:
-        page.goto(f"https://{DOMAIN}.eljur.ru/authorize?return_uri=%2Fjournal-board-action")
+
         try:
+            # Launch the browser
+            browser = p.chromium.launch()
+            logging.debug("browser opened")
+
+            # Open a new browser page
+            page = browser.new_page()
+
+            # Create a URI for our test file
+
+            # Open our test file in the opened page
+            page.goto(f"https://{DOMAIN}.eljur.ru/authorize?return_uri=%2Fjournal-board-action")
+
             # Log In
             login_field = page.locator('[type="text"]')
             password_field = page.locator('[type="password"]')
@@ -31,40 +33,36 @@ def scrape():
 
             submit_button = page.locator('[type="submit"]')
             submit_button.click()
-        except Exception as error:
-            logging.debug(f"Error while request: {str(error)}")
-            page.goto(f"https://{DOMAIN}.eljur.ru/journal-board-action?user={LOGIN}&domain={DOMAIN}")
-            pass
-    
-        page.wait_for_url(f"https://{DOMAIN}.eljur.ru/journal-board-action?user={LOGIN}&domain={DOMAIN}")
-        page.wait_for_load_state("domcontentloaded")
-        if page.url != f"https://{DOMAIN}.eljur.ru/journal-board-action?user={LOGIN}&domain={DOMAIN}" and page.url != f"https://{DOMAIN}.eljur.ru/journal-board-action":
-            page.goto(f"https://{DOMAIN}.eljur.ru/journal-board-action")
-            page.wait_for_load_state("domcontentloaded")
-        
-        page_content = page.content()
 
-        new_content = page.locator('[class="board-item active"]').first
+            page.wait_for_url(f"https://{DOMAIN}.eljur.ru/journal-board-action?user={LOGIN}&domain={DOMAIN}")
-        try:
+    #            page.wait_for_load_state("domcontentloaded")
-            new_content.screenshot(path = "data/screenshot.png")
+            
-        except FileNotFoundError:
+            page_content = page.content()
-            mkdir("data")
+
-            logging.info("can`t take screenshot")
+            new_content = page.locator('[class="board-item active"]').first
-            logging.info("retry")
+            try:
-            new_content.screenshot(path = "data/screenshot.png")
+                new_content.screenshot(path = "data/screenshot.png")
+            except FileNotFoundError:
+                mkdir("data")
+                logging.info("can`t take screenshot")
+                logging.info("retry")
+                new_content.screenshot(path = "data/screenshot.png")
+            except:
+                logging.error("can`t take screenshot")
+
+            # Close browser
+            browser.close()
+            logging.debug("browser closed")
+
+            # Process extracted content with BeautifulSoup
+            soup = BeautifulSoup(page_content, features="lxml")
+
+            logging.debug("content extracted")
+    #        return '\n'.join(el.strip() for el in str(soup.get_text).split('\n') if el.strip())
+            return str(soup.get_text)
+        except _api_types.TimeoutError:
+            logging.error("connection timed out")
+            return " "
         except:
-            logging.error("can`t take screenshot")
+            logging.error(f"Error while request: {Exception}")
-
+            return " "
-        # Process extracted content with BeautifulSoup
-        soup = BeautifulSoup(page_content, features="lxml")
-
-        logging.debug("content extracted")
-#        return '\n'.join(el.strip() for el in str(soup.get_text).split('\n') if el.strip())
-        return str(soup.get_text)
-    
-    except _api_types.TimeoutError:
-        logging.error("connection timed out")
-        return " "
-    except Exception as error:
-        logging.error(f"Error while request: {str(error)}")
-        return " "