Convert 10-K document into a dataframe
Budget: £20 – £250 GBP
10-K document:
Example:
- https://www.sec.gov/Archives/edgar/data/1526520/000095017023003200/trip-20221231.htm
Using python code, do the following:
1. Extract all the links to 10-K document given stock ticker / CIK
2. Extract all the paragraphs in the 10-K document
3. Have to extract paragraph styles, such as bold, italic, underline, font-size etc.
4. Add additional metadata of the paragraphs: belong to which Item (Item 1: business, item 2: risk factors...).
5. Add metadata, including stock ticker, document date, cik, fiscal year filing.
6. Give a sentiment score for that paragraph
7. Convert all paragraphs into data frame
Example:
- https://www.sec.gov/Archives/edgar/data/1526520/000095017023003200/trip-20221231.htm
Using python code, do the following:
1. Extract all the links to 10-K document given stock ticker / CIK
2. Extract all the paragraphs in the 10-K document
3. Have to extract paragraph styles, such as bold, italic, underline, font-size etc.
4. Add additional metadata of the paragraphs: belong to which Item (Item 1: business, item 2: risk factors...).
5. Add metadata, including stock ticker, document date, cik, fiscal year filing.
6. Give a sentiment score for that paragraph
7. Convert all paragraphs into data frame