Skip to content

Chapta error  #296

@alby696

Description

@alby696

Trying to scrape the Mediaworld site I get the error that no information is found.
Result
{'answer': 'It is not possible to get the list of all products, description and price from the discarded content because there is no product information within the content. The content contains error messages and user instructions, but does not provide any product information."}

Running the test with another scraper via laravel, I can see that the site returns this wording:
Dear visitor,
Unfortunately, this happened too fast for us. To continue and to see all offers from Mediamarkt, please complete the captcha below.
Please turn JavaScript on and reload the page.Please enable Cookies and reload the page.

Thanks

Code

`from scrapegraphai.graphs import SmartScraperGraph
import nest_asyncio
nest_asyncio.apply()

graph_config = {
"llm" : {
"model" : "ollama/llama3",
"temperature" : 0,
"format" : "json",
"base_url" : "http://localhost:11434",
},
"embeddings" : {
"model" : "ollama/nomic-embed-text",
"base_url" : "http://localhost:11434",
},
"verbose" : True,
}

smart_scraper_graph = SmartScraperGraph (
prompt = "List me the product with their price",
source = "https://www.mediaworld.it/it/brand/apple/iphone/iphone-15-pro",
config = graph_config
)

result = smart_scraper_graph.run()

print(result)`

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions