Extract the readable content from the Web Page
#25
by
gunjansa
- opened
Hi, I am trying to use the NuExtract for extracting all the text content from the Web Page which is suitable for reading for the user.
But I am unable to create a suitable prompt. Any recommendations will be helpful. Different templates used are:
template = """{
"Page Title": "",
"Content": ""
}"""
template = """{
"Page Title": "",
"main_text": ""
}"""
template = """{
"title": "",
"author": "",
"published_date": "",
"article_paragraphs": []
}"""
template = """{
"title": "",
"author": "",
"published_date": "",
"full_article_text": "",
"language": ""
}"""