vara.txt

*** Settings ***
Library    RPA.Browser.Selenium    auto_close=${False}
Library    Collections
Library    RPA.Tables
Library    RPA.PDF
Library    OperatingSystem

*** Variables ***
${PDF_FILE}                      ./output/screenshots-duunitori/pdf/website_info.pdf
${SCREENSHOT_DIRECTORY}          ./output/screenshots-duunitori
${TITLE_SCREENSHOT_DIRECTORY}    ./output/screenshots-duunitori/titles
${PDF_DIRECTORY}                 ./output/screenshots-duunitori/pdf
${MAX_RETRIES}                   3    # Max retries per job listing in case of errors

*** Tasks ***
Avaa verkkosivu ja tallenna työilmoitukset PDF-tiedostoon
    Open Duunitori Website
    Lisää hakusanat
    ${job_data}=    Avaa hakemukset ja ota screenshot 
    Kokoa PDF    ${job_data}

*** Keywords ***
Open Duunitori Website
    Open Available Browser    https://www.duunitori.fi
    Maximize Browser Window

Lisää hakusanat
    Delete All Cookies
    Click Element When Visible    xpath://button[text()='Hyväksy evästeet']
    Execute JavaScript    var element = document.querySelector("div.form__input.form__input--fake.form__input--border.form__input--icon.js-nav-toggle-search"); element.innerText = "It"; element.dispatchEvent(new Event('input', { bubbles: true }));
    Input Text    css:.taggle_input    IT 
    Press Keys    css:.taggle_input    TAB
    Input Text    css:.taggle_input    designer
    Press Keys    css:.taggle_input    TAB
    Input Text    css:.taggle_input    developer
    Press Keys    css:.taggle_input    TAB
    Press Keys    None    Pääkaupunkiseutu   
    Click Element    js-form__search--submit 
    Execute JavaScript    document.evaluate("//button[contains(text(), 'Uusimmat')]", document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.click();

Avaa hakemukset ja ota screenshot
    ${job_data}=    Create List
    Wait Until Element Is Visible    xpath://a[contains(@class, 'job-box__hover')]
    ${job_elements}=    Get WebElements    xpath://a[contains(@class, 'job-box__hover') and contains(@class, 'gtm-search-result')]

    FOR    ${index}    IN RANGE    0    20
        ${job_elements}=    Get WebElements    xpath://a[contains(@class, 'job-box__hover') and contains(@class, 'gtm-search-result')]
        Exit For Loop If    ${index} >= ${job_elements.__len__()}
        ${job_element}=    Get From List    ${job_elements}    ${index}
        
        Scroll Element Into View    ${job_element}
        Wait Until Element Is Visible    ${job_element}
        Sleep    2s

        # Click the job listing and handle loading
        Click Element    ${job_element}
        Sleep    5s

        # Set the window to full page height
        ${original_size}=    Get Window Size
        ${total_height}=    Execute JavaScript    return document.body.scrollHeight
        Set Window Size    ${original_size}[0]    ${total_height}
        Sleep    5s

        # Capture full page screenshot
        ${screenshot_path}=    Set Variable    ${SCREENSHOT_DIRECTORY}/full_screenshot_${index + 1}.png
        Capture Page Screenshot    ${screenshot_path}
        ${screenshot_exists}=    Run Keyword And Return Status    File Should Exist    ${screenshot_path}
        
        # Log and continue if screenshot is missing
        Run Keyword If    '${screenshot_exists}' == 'FAIL'    Log To Console    "Failed to capture full page screenshot for listing ${index + 1}, skipping."    AND    Continue For Loop

        # Capture the <h1> title element screenshot
        Wait Until Element Is Visible    xpath://h1
        ${title_screenshot_path}=    Set Variable    ${TITLE_SCREENSHOT_DIRECTORY}/title_screenshot_${index + 1}.png
        Capture Element Screenshot    xpath://h1    ${title_screenshot_path}
        ${title_screenshot_exists}=    Run Keyword And Return Status    File Should Exist    ${title_screenshot_path}

        # Log and continue if title screenshot is missing
        Run Keyword If    '${title_screenshot_exists}' == 'FAIL'    Log To Console    "Failed to capture title screenshot for listing ${index + 1}, skipping."    AND    Continue For Loop

        # Get the current URL
        ${current_url}=    Get Location
        ${job_entry}=    Create Dictionary    url=${current_url}    full_screenshot=${screenshot_path}    title_screenshot=${title_screenshot_path}
        Append To List    ${job_data}    ${job_entry}

        # Revert window size after the screenshot
        Set Window Size    ${original_size}[0]    ${original_size}[1]
        Sleep    5s

        # Navigate back to the job list
        Go Back
        Wait Until Element Is Visible    xpath://a[contains(@class, 'job-box__hover')]
        Sleep    2s
    END

    # Return the collected job data
    [Return]    ${job_data}

Kokoa PDF
    [Arguments]    ${job_data}

    # Initialize HTML content for PDF
    ${html_content}=    Set Variable    <html><body><h1>Job Listings Information</h1>

    # Loop through each job entry and add it to the HTML content
    FOR    ${job}    IN    @{job_data}
        ${url}=    Get From Dictionary    ${job}    url
        ${full_screenshot}=    Get From Dictionary    ${job}    full_screenshot
        ${title_screenshot}=    Get From Dictionary    ${job}    title_screenshot

        ${html_content}=    Set Variable    ${html_content}<h2>Job Listing</h2><p>URL: <a href="${url}">${url}</a></p>
        ${html_content}=    Set Variable    ${html_content}<h3>Full Page Screenshot</h3><img src="${full_screenshot}" width="600" height="800"><br>
        ${html_content}=    Set Variable    ${html_content}<h3>Title Screenshot</h3><img src="${title_screenshot}" width="600" height="200"><br>
    END

    ${html_content}=    Set Variable    ${html_content}</body></html>

    Log To Console    "Generating PDF at path: ${PDF_FILE}"
    HTML To PDF    ${html_content}    ${PDF_FILE}

    Log To Console    Website information has been saved to ${PDF_FILE}





    file ongelmat:



    *** Settings ***
Library    RPA.Browser.Selenium    auto_close=${False}
Library    Collections
Library    RPA.Tables
Library    RPA.PDF
Library    OperatingSystem
Library    BuiltIn

*** Variables ***
${SCREENSHOT_DIRECTORY}          ./screenshots-duunitori
${PDF_DIRECTORY}                 ./output/screenshots-duunitori/pdf
${PDF_FILE}                      ${PDF_DIRECTORY}/job_listings.pdf

*** Tasks ***
Avaa verkkosivu ja tallenna työilmoitukset PDF-tiedostoon
    # Ensure directories exist
    Create Directory    ${SCREENSHOT_DIRECTORY}
    Create Directory    ${PDF_DIRECTORY}
    
    Open Duunitori Website
    Lisää hakusanat
    ${job_data}=    Avaa hakemukset ja ota screenshot 
    Kokoa PDF    ${job_data}

*** Keywords ***

Convert Image To Base64
    [Arguments]    ${image_path}
    ${image_data}=    Get File    ${image_path}    binary=True
    ${base64_data}=    Evaluate    import base64; base64.b64encode(${image_data}).decode('utf-8')    modules=base64
    [Return]    ${base64_data}


Open Duunitori Website
    Open Available Browser    https://www.duunitori.fi
    Maximize Browser Window

Lisää hakusanat
    Delete All Cookies
    Click Element When Visible    xpath://button[text()='Hyväksy evästeet']
    Execute JavaScript    var element = document.querySelector("div.form__input.form__input--fake.form__input--border.form__input--icon.js-nav-toggle-search"); element.innerText = "It"; element.dispatchEvent(new Event('input', { bubbles: true }));
    Input Text    css:.taggle_input    IT 
    Press Keys    css:.taggle_input    TAB
    Input Text    css:.taggle_input    designer
    Press Keys    css:.taggle_input    TAB
    Input Text    css:.taggle_input    developer
    Press Keys    css:.taggle_input    TAB
    Press Keys    None    Pääkaupunkiseutu   
    Click Element    js-form__search--submit 
    Execute JavaScript    document.evaluate("//button[contains(text(), 'Uusimmat')]", document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.click();

Avaa hakemukset ja ota screenshot
    ${job_data}=    Create List
    Wait Until Element Is Visible    xpath://a[contains(@class, 'job-box__hover')]
    ${job_elements}=    Get WebElements    xpath://a[contains(@class, 'job-box__hover') and contains(@class, 'gtm-search-result')]

    FOR    ${index}    IN RANGE    0    20
        # Re-fetch the list of job elements to avoid stale references
        ${job_elements}=    Get WebElements    xpath://a[contains(@class, 'job-box__hover') and contains(@class, 'gtm-search-result')]

        # Ensure there are enough elements
        Exit For Loop If    ${index} >= ${job_elements.__len__()}

        ${job_element}=    Get From List    ${job_elements}    ${index}
        
        # Scroll to the element and wait until it is clickable
        Scroll Element Into View    ${job_element}
        Wait Until Element Is Visible    ${job_element}
        Sleep    2s    # Adjust if necessary

        # Click the element and wait for page load
        Click Element    ${job_element}
        Sleep    5s

        # Set the window to full page height for capturing the full page screenshot
        ${original_size}=    Get Window Size
        ${total_height}=    Execute JavaScript    return document.body.scrollHeight
        Set Window Size    ${original_size}[0]    ${total_height}

        # Take a full page screenshot with a unique filename
        ${screenshot_path}=    Set Variable    ${SCREENSHOT_DIRECTORY}/full_screenshot_${index + 1}.png
        Capture Page Screenshot    ${screenshot_path}
        File Should Exist    ${screenshot_path}    # Ensure the screenshot was saved

        # Get the current URL
        ${current_url}=    Get Location
        ${job_entry}=    Create Dictionary    url=${current_url}    screenshot=${screenshot_path}
        Append To List    ${job_data}    ${job_entry}

        # Revert window size after the screenshot
        Set Window Size    ${original_size}[0]    ${original_size}[1]
        Sleep    7s

        # Navigate back to the job list with retry mechanism
        Navigate Back With Retry

    END
    [Return]    ${job_data}

Navigate Back With Retry
    ${max_retries}=    Set Variable    7    # Set maximum retry attempts
    ${attempt}=        Set Variable    0

    FOR    ${attempt}    IN RANGE    ${max_retries}
        Go Back
        Sleep    2s
        ${element_visible}=    Run Keyword And Return Status    Wait Until Element Is Visible    xpath://a[contains(@class, 'job-box__hover')]    timeout=5s
        IF    ${element_visible}
            Log    Successfully navigated back on attempt ${attempt + 1}
            Exit For Loop
        ELSE
            Log    Attempt ${attempt + 1} to go back failed, retrying...
            Sleep    2s
        END
    END

    # If it still doesn't see the element after max retries, log a warning
    Run Keyword If    not ${element_visible}    Log To Console    "WARNING: Could not return to the job list after ${max_retries} attempts."


Kokoa PDF
    [Arguments]    ${job_data}

    # Initialize HTML content for PDF
    ${html_content}=    Set Variable    <html><body><h1>Job Listings Information</h1>

    # Loop through each job entry and add it to the HTML content
    FOR    ${job}    IN    @{job_data}
        ${url}=    Get From Dictionary    ${job}    url
        ${screenshot}=    Get From Dictionary    ${job}    screenshot

        # Convert images to base64
        ${screenshot_base64}=    Convert Image To Base64    ${screenshot}

        # Embed images in HTML content with base64 data
        ${html_content}=    Set Variable    ${html_content}<h2>Job Listing</h2><p>URL: <a href="${url}">${url}</a></p>
        ${html_content}=    Set Variable    ${html_content}<h3>Full Page Screenshot</h3><img src="data:image/png;base64,${screenshot_base64}" width="600" height="800"><br>
    END

    ${html_content}=    Set Variable    ${html_content}</body></html>

    # Ensure PDF directory exists
    Create Directory    ${PDF_DIRECTORY}

    Log To Console    "Generating PDF at path: ${PDF_FILE}"
    HTML To PDF    ${html_content}    ${PDF_FILE}

    Log To Console    "Website information has been saved to ${PDF_FILE}"