read_dataset_lexrank.py

! wget http://mlg.ucd.ie/files/datasets/bbc-fulltext.zip
! unzip bbc-fulltext.zip

project_path = "/text_summarization/"

documents = []
documents_dir = Path('/content/bbc/entertainment')

for file_path in documents_dir.files('*.txt'):
    with file_path.open(mode='rt', encoding='utf-8') as fp:
        documents.append(fp.readlines())