edgar-crawler

finance natural-language-processing

The only open-source toolkit that can download SEC EDGAR financial reports and extract textual data from specific item sections into nice & clean structured JSON files. Presented at WWW 2025 @ Sydney, Australia (https://dl.acm.org/doi/10.1145/3701716.3715289)

How to download and setup edgar-crawler

Open terminal and run command

git clone https://github.com/lefterisloukas/edgar-crawler.git

git clone is used to create a copy or clone of edgar-crawler repositories. You pass git clone a repository URL.
it supports a few different network protocols and corresponding URL formats.

Also you may download zip file with edgar-crawler https://github.com/lefterisloukas/edgar-crawler/archive/master.zip

Or simply clone edgar-crawler with SSH

[email protected]:lefterisloukas/edgar-crawler.git

If you have some problems with edgar-crawler

You may open issue on edgar-crawler support forum (system) here: https://github.com/lefterisloukas/edgar-crawler/issues

Similar to edgar-crawler repositories

Here you may see edgar-crawler alternatives and analogs

math-php natural-language-processing lectures spaCy HanLP gensim MatchZoo tensorflow-nlp Awesome-pytorch-list awesome-quant spacy-models Repo-2017 Lean stanford-tensorflow-tutorials awesome-nlp nlp_tasks nltk pattern TextBlob CoreNLP allennlp mycroft-core practical-pytorch textract languagetool MITIE machine_learning_examples prose arXivTimes ltp