| Here's the prompt. The project is pretty simple, just a Jupyter notebook calling your configured LLM with this prompt. Your goal is to write Selenium code to answer queries. Your answer must be a Python markdown only.
You can have access to external websites and libraries. You can assume the following code has been executed:
```python
from selenium import webdriver
from selenium.webdriver.common.by import By driver = webdriver.Firefox()
``` --- HTML:
<!DOCTYPE html>
<html>
<head>
<title>Mock Search Page</title>
</head>
<body>
<h1>Search Page Example</h1>
<input id="searchBar" type="text" placeholder="Type here to search...">
<button id="searchButton">Search</button>
<script>
document.getElementById('searchButton').onclick = function() {{
var searchText = document.getElementById('searchBar').value;
alert("Searching for: " + searchText);
}};
</script>
</body>
</html> Query: Click on the search bar 'Type here to search...', type 'selenium', and press the 'Enter' key Completion:
```python
# Let's proceed step by step.
# First we need to identify the component first, then we can click on it. # Based on the HTML, the link can be uniquely identified using the ID "searchBar"
# Let's use this ID with Selenium to identify the link
search_bar = driver.find_element(By.XPATH, "//[@id='searchBar']") search_bar.click() # Now we can type the asked input
search_bar.send_keys("selenium") # Finally we can press the 'Enter' key
search_bar.send_keys(Keys.ENTER)
``` --- HTML:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Mock Page for Selenium</title>
</head>
<body>
<h1>Welcome to the Mock Page</h1>
<div id="links">
<a href="#link1" id="link1">Link 1</a>
<br>
<a href="#link2" class="link">Link 2</a>
<br>
</div>
</body>
</html> Query: Click on the title Link 1 and then click on the title Link 2 Completion:
```python
# Let's proceed step by step.
# First we need to identify the first component, then we can click on it. Then we can identify the second component and click on it. # Based on the HTML, the first link the link can be uniquely identified using the ID "link1"
# Let's use this ID with Selenium to identify the link
link_to_click = driver.find_element(By.XPATH, "//[@id='link1']") # Then we click on the link
link_to_click.click() It then goes on with several other examples. Basically its few shot learning, with a few examples of instructions, HTML and selenium code to execute those instructions. Then you give it your new instruction and it generates selenium code for those. |