def get_titles(): titles_english = MdFile.get_metadata_field_values( md_files=raamaayana.get_adhyaaya_md_files(md_file_path), field_name="title") unnumbered_titles = [ regex.sub("^[०-९0-9]+ ", "", x) for x in titles_english ] logging.info("\n".join(unnumbered_titles))
def get_audio_file_data(): urls = list( library.get_audio_file_urls( md_files=raamaayana.get_adhyaaya_md_files(md_file_path))) titles_from_urls = [ regex.match(r".+\d\d\d-(.+?)(_0)?.mp3", url.replace("\n", "")).group(1).replace("_", " ") for url in urls ] logging.info("\n".join(urls))
def reformat_audio_tag(): adhyaaya_to_source_file_map = raamaayana.get_adhyaaya_to_source_file_map() # logging.debug(adhyaaya_to_mp3_map) dest_md_files = raamaayana.get_adhyaaya_md_files( md_file_path= "/home/vvasuki/vvasuki-git/kAvya/content/TIkA/padyam/purANam/rAmAyaNam/AndhrapAThaH" ) logging.debug(dest_md_files) for md_file in dest_md_files: # md_file.replace_in_content("<div class=\"audioEmbed\".+?></div>\n", "") logging.debug(md_file.file_path) (kaanda, adhyaaya) = raamaayana.get_kaanda_adhyaaya(md_file) adhyaaya_id = "%s-%s" % (kaanda, adhyaaya) logging.debug(adhyaaya_id) (yml, current_content) = md_file._read_yml_md_file() audio_tag = regex.findall("<div class.*div>", current_content.replace("\n", " "))[0] (_, target_content ) = adhyaaya_to_source_file_map[adhyaaya_id]._read_yml_md_file() # logging.debug(adhyaaya_to_source_file_map[adhyaaya_id]) md_file.replace_content("%s\n\n%s" % (audio_tag, target_content), dry_run=False)
import logging from curation_projects import raamaayana from doc_curation.md_helper import MdFile # Remove all handlers associated with the root logger object. for handler in logging.root.handlers[:]: logging.root.removeHandler(handler) logging.basicConfig( level=logging.DEBUG, format="%(levelname)s:%(asctime)s:%(module)s:%(lineno)d %(message)s") md_file_path = "/home/vvasuki/vvasuki-git/kAvya/content/TIkA/padyam/purANam/rAmAyaNam/AndhrapAThaH" # MdFile.fix_index_files(dir_path=md_file_path, dry_run=False) # MdFile.fix_titles( # md_files=raamaayana.get_adhyaaya_md_files(md_file_path), # spreadhsheet_id="1xqVBhDwRzcEL7HlCJhxmnG1aOFFk6B8gGZ4GuBZynf8", # worksheet_name="शीर्षिकाः", id_column="id", title_column="अन्तिमशीर्षिका", md_file_to_id=raamaayana.get_adhyaaya_id, dry_run=False # ) MdFile.devanaagarify_titles( md_files=raamaayana.get_adhyaaya_md_files(md_file_path), dry_run=False)
def get_numbers(): titles_english = MdFile.get_metadata_field_values( md_files=raamaayana.get_adhyaaya_md_files(md_file_path), field_name="title_english") numbers = [regex.sub("^([०-९0-9]+) .+", "\\1", x) for x in titles_english] logging.info("\n".join(numbers))
kaanda = regex.findall("Kanda_\\d_", str(mp3_path))[0].replace("Kanda", "").replace("_", "") adhyaaya = regex.findall("\\d\\d\\d", str(mp3_path))[0] adhyaaya_id = "%s-%s" % (kaanda, adhyaaya) web_mp3_path = str(mp3_path).replace( mp3_root, "https://archive.org/download/Ramayana-recitation-Sriram-harisItArAmamUrti-Ghanapaati-v2/" ).replace("mp3/", "") adhyaaya_to_mp3_map[adhyaaya_id] = web_mp3_path return adhyaaya_to_mp3_map if __name__ == '__main__': adhyaaya_to_mp3_map = get_adhyaaya_to_mp3_map() # logging.debug(adhyaaya_to_mp3_map) for md_file in raamaayana.get_adhyaaya_md_files( md_file_path= "/home/vvasuki/vvasuki-git/kAvya/content/TIkA/padya/purANa/rAmAyaNa/Andhra/" ): # md_file.replace_in_content("<div class=\"audioEmbed\".+?></div>\n", "") logging.debug(md_file.file_path) (kaanda, adhyaaya) = raamaayana.get_kaanda_adhyaaya(md_file) adhyaaya_id = "%s-%s" % (kaanda, adhyaaya) logging.debug(adhyaaya_id) (yml, _) = md_file.read_md_file() # logging.debug(adhyaaya_to_mp3_map[adhyaaya_id]) md_file.prepend_to_content( '<div class="audioEmbed" caption="श्रीराम-हरिसीताराममूर्ति-घनपाठिभ्यां वचनम्" src="%s"></div>\n' % adhyaaya_to_mp3_map[adhyaaya_id], dry_run=False)