Walmart screenshot script is finalized for Azure functions

Scripts/Walmart/Spark/screenshots_to_pdf.py

@@ -0,0 +1,105 @@
+import re
+import sys
+from playwright.sync_api import sync_playwright, Playwright
+from PIL import Image
+import glob
+import os
+from datetime import date
+
+
+BASEURL = "https://walmart.northpass.com/app/courses/"
+USERID = "?uid=7beg87y4-fh24-4929-3rt5-24kdn87s5241"
+COURSEID = sys.argv[1]
+DIR = "./"
+
+def run(playwright: Playwright):
+    print("running")
+    webkit = playwright.webkit
+    browser = webkit.launch()
+    context = browser.new_context(
+          viewport={ 'width': 390, 'height': 844 }
+    )
+    page = context.new_page()
+    screen_num = 0
+
+    # Navigate to and screenshot the title page
+    page.goto(f"{BASEURL}{COURSEID}{USERID}")
+    course_name = page.locator('.header-title').evaluate("node => node.innerText")
+    print(course_name)
+
+    # Extract all hrefs from the course outline
+    course_links = page.locator('.np-course-outline-content-section a').evaluate_all('elements => elements.map(el => el.href)')
+    page.screenshot(path=f"{DIR}-{course_name}_{screen_num}.png", full_page=True)
+
+    print("Course outline links:")
+    for idx, link in enumerate(course_links):
+        screen_num += 1
+        print(f"{idx + 1}. {link}")
+        page.goto(f"{link}")
+        page.screenshot(path=f"{DIR}-{course_name}_{screen_num}.png", full_page=True)
+    browser.close()
+    # find_pictures()
+
+
+def find_pictures(DIR):
+    files = []
+    listfiles = glob.glob(DIR + "*.png")
+    for file in listfiles:
+        files.append(os.path.basename(file))
+        # Now file will only show the file name, not the entire path
+    split_resources(files, DIR)
+
+
+def split_resources(files, DIR):
+    try:
+        resource_title = files[0][:-6]
+        # resource_title = resource_title[:-6]
+        files.sort()
+        new_list = []
+        for file in files:
+            if resource_title in file:
+                new_list.append(file)
+        for item in new_list:
+            files.remove(item)
+        split_resources(files, DIR)
+        process_pictures(new_list, resource_title, DIR)
+    except IndexError as e:
+        print(e)
+    finally:
+        pass
+
+
+def process_pictures(new_list, resource_title, DIR):
+    resource_title = re.sub(r'[?]', "", resource_title)
+    today = date.today()
+    today = today.strftime("%m.%d.%Y")
+    image_list = []
+    resource = Image.open(new_list[0])
+    resource = resource.convert("RGB")
+    for picture in new_list[1:]:
+        image = Image.open(picture)
+        converted = image.convert("RGB")
+        image_list.append(converted)
+        # image_list.append(image)
+    resource.save(
+        DIR + f"PDFs/{resource_title}_{today}.pdf",
+        save_all=True,
+        append_images=image_list,
+    )
+
+
+def delete_originals(DIR):
+    path = glob.glob(DIR + "*.png")
+    for file in path:
+        try:
+            os.remove(file)
+        except TypeError as e:
+            print("Error!")
+            print(e)
+    print("All Done")
+
+
+with sync_playwright() as playwright:
+    run(playwright)
+    find_pictures(DIR)
+    delete_originals(DIR)