a python script to roughly tabulate the Sci-Fi London 2020 short films programme from a downloaded copy of the webpage

summarise-shorts.py

#! /usr/bin/env python3

import html.parser
import contextlib
import re
import csv

text_pattern = re.compile(r'([A-Z ()&!0-9]+) \(([^)]+)\) (.*)')
meta_pattern = re.compile(r'Dir: ([^,]+),? ([A-Za-z ]+), ([^0-9]+), ([0-9]+) ?mins?.?')

def parse(s, pattern):
	m = pattern.match(s)
	if not m: raise ValueError(s)
	return m.groups()

class ShortsParser(html.parser.HTMLParser, contextlib.AbstractContextManager):
	def __init__(self, output):
		super().__init__()
		self.output = output
		self.text = None

	def handle_starttag(self, tag, attrs_list):
		attrs = dict(attrs_list)
		if tag == 'tr' and attrs['class'] and attrs['class'].startswith('row-'):
			self.index = int(attrs['class'].split(' ')[0].split('-')[1])
		elif tag == 'img':
			self.img_src = attrs['src']
		elif tag == 'td' and attrs['class'] and attrs['class'] == 'column-2':
			self.text = ''

	def handle_data(self, data):
		if self.text is not None:
			self.text = self.text + data

	def handle_endtag(self, tag):
		if tag == 'tr':
			text = ' '.join(self.text.split())
			text_match = text_pattern.match(text)
			if not text_match: raise ValueError(text)
			title_upper, meta, description = parse(text, text_pattern)
			title = title_upper.title()
			director, country, language, length_str = parse(meta, meta_pattern)
			length = int(length_str)
			
			self.output(self.index, self.img_src, title, director, country, language, length, description)

	def __exit__(self, exc_type, exc_value, traceback):
		self.close()


with open('shorts.csv', 'w', newline='') as out_file:
	out = csv.writer(out_file)
	out.writerow(('index', 'image', 'title', 'director', 'country', 'language', 'length', 'description'))
	def write_film(index, img_src, title, director, country, language, length, description):
		print(index, title)
		out.writerow((str(index), f'=IMAGE("{img_src}")', title, director, country, language, str(length), description))
	with ShortsParser(write_film) as parser:
		with open('shorts.html') as in_file:
			for line in in_file:
				parser.feed(line)