import json f = open("content.md", "r") content = f.read() algaes_dicts = [] for algae in content.split("----"): algdict = {} for line in algae.split("\n"): if line.startswith("# "): Title = line.replace("# ", "") algdict["title"] = Title if line.startswith("## B"): bio_header = line.replace("## Biomass: ", "") algdict["b_header"] = bio_header if line.startswith("## P"): pig_header = line.replace("## Pigment: ", "") algdict["p_header"] = pig_header if line.startswith("### B"): bio_body = line.replace("### Biomass: ", "") algdict["b_body"] = bio_body if line.startswith("### P"): pig_body = line.replace("### Pigment: ", "") algdict["p_body"] = pig_body if line.startswith("#### "): main = line.replace("#### ", "") algdict["main"] = main if line.startswith("##### "): list_info = line.replace("##### ", "") algdict["list_info"] = list_info algaes_dicts.append(algdict) json = json.dumps(algaes_dicts, sort_keys=True, indent=4) f = open("formatted_content.json", "w") f.write(json) f.close()