def transcript(): link_again = summ.the_link the_props = float(request.form['proportion']) print("Downloading Video") tuple = dl_youtube.video_download(link_again, 22) vtt = tuple[1] video = tuple[0] print("Loading Transcript") file = punctuate_transcript(vtt) print("Summarizing Lecture") with open(file[:-4] + "_sum.txt", "w+") as lex_rank_summary_file: lex_rank_summary_file.write( sumy_lex_rank.lex_rank_summarizer(file, the_props)) print("Finding TimeStamps") times = video_indices.video_indices(vtt, file[:-4] + "_sum.txt") print('Rendering Video') final = edit_video.edit_summarized_video(video, times) return render_template("transcript.html", final_video=final)
import dl_youtube import puncuator import model_utilities def lsa_summarizer(file): parser = PlaintextParser.from_file(file, Tokenizer("english")) summarizer = LsaSummarizer() text = open(file, 'r').read() chosen_sentences = summarizer(parser.document, model_utilities.summary_length(text)) summary = "" for sentence_tuple in chosen_sentences: line = "" for i in range(len(sentence_tuple.words)): if i == len(sentence_tuple.words) - 1: line += sentence_tuple.words[i] + "." else: line += sentence_tuple.words[i] + " " summary += line + " " return summary url = "https://www.youtube.com/watch?v=1qy9xVEOI40" vtt = dl_youtube.video_download(url, 22)[1] file = puncuator.punctuate_transcript(vtt) with open("lsa_summary.txt", "w+") as lsa_summary_file: lsa_summary_file.write(lsa_summarizer(file))