Can source part use selenium driver.page_source?

[JamesGGGG]

Describe the bug
error missing "content"

smart_scraper_graph = SmartScraperGraph(
prompt="summarize information in this page.",

also accepts a string with the already downloaded HTML code

source=driver.page_souce,
config=graph_config
)
result = smart_scraper_graph.run()

error: 'Input to PromptTemplate is missing variables {'"content"'}. Expected: ['"content"', 'question'] Received: ['question']\nNote: if you intended {"content"} to be part of the string and not a variable, please escape it with double curly braces like: '{{"content"}}'.\nFor troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/INVALID_PROMPT_INPUT '

Other way:
html_file_path = self.save_page_source(headless_driver, "information")
with open(html_file_path, 'r', encoding='utf-8') as file:
html_content = file.read()
smart_scraper_graph = SmartScraperGraph(
prompt="summarize information in this page.",

also accepts a string with the already downloaded HTML code

source=html_content,
config=graph_config
)

result = smart_scraper_graph.run()

error remains the same

Desktop (please complete the following information):

• OS: mac os
• Browser chrome
• Version

Additional context
I created a selenium driver to get a url, after login, click some buttons, get to a page, I hope scrapegraphai can help me scrape informations in the page.

[dosubot]

Hey @JamesGGGG! I'm Dosu, a bot here to help you with bugs, questions, and becoming a contributor. I'll assist you while you wait for a human maintainer. 😊

To resolve the 'Input to PromptTemplate is missing variables {"content"}' error when using SmartScraperGraph with Selenium's driver.page_source or a saved HTML file, you can try downgrading the scrapegraphai library to version 1.37.0. This has been suggested as a solution for similar issues. You can do this by running the following command:

pip install scrapegraphai==1.37.0

Additionally, ensure that the source parameter is correctly receiving the HTML content and that all required variables are provided to the PromptTemplate ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[JamesGGGG]

It worked. Another question, I want the scraped information to fill a data class, can it is possible or what kind of action should I do?

[VinciGit00]

what do you mean by information to fill a data class? you can specify an output schema If you want