Parses the interview files provided by http://usesthis.com

usesthis_interview_parser.py

# -*- coding: utf-8 -*-

from re import match, findall, DOTALL
from os import listdir
from os.path import dirname, abspath

from unipath import Path

import yaml

import markdown

INTERVIEW_FILES_DIRECTORY = Path(abspath(__file__)).ancestor(1).child('usesthis').child('_posts')

INTERVIEW_FILE_EXTENSION = ".interview"

UNWANTED_KEYS = ['slug', 'summary', 'layout', 'credits']

HEADER_REGEX = "(?P<yml>^---.*)\n---"
WORDS_REGEX = '\[([^\[\(\)]+)\]\[([a-z0-9\.\-]+)?\]'



def main():
    filenames = get_files()
    md = markdown.Markdown()
    interviews = []
    for filename in filenames:
        with open(INTERVIEW_FILES_DIRECTORY.child(filename), 'r') as md_file:
            md_string = md_file.read()
            yml_header = match(HEADER_REGEX, md_string, DOTALL).groupdict()['yml']
            interview = yaml.load(yml_header)
            # Remove unwanted keys
            for key in UNWANTED_KEYS:
                if key in interview:
                    del interview[key]
            existing_words = [words[1] for words in findall(WORDS_REGEX, md_string) if words[1]]
            interview['words'] = existing_words
            interviews.append(interview)
    return interviews




def get_files():
    names = [filename 
        for filename in listdir(INTERVIEW_FILES_DIRECTORY) if filename.endswith(INTERVIEW_FILE_EXTENSION)
    ]
    return names



if __name__ == "__main__":
    main()