generate-samples

#!/usr/bin/env python

from html.parser import HTMLParser
from os.path import basename, splitext
import subprocess
from urllib.request import urlopen
from urllib.parse import urlparse

OUTPUT_FOLDER = 'samples'
REGION = 'eu-west-1'

sample_templates_services = f'https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/sample-templates-services-{REGION}.html'
sample_templates_appframeworks = f'https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/sample-templates-appframeworks-{REGION}.html'
sample_templates_applications = f'https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/sample-templates-applications-{REGION}.html'
sample_templates_resources = f'https://aws.amazon.com/cloudformation/resources/templates/{REGION}/'

EXAMPLES_URLS = [
    sample_templates_services, sample_templates_appframeworks,
    sample_templates_applications, sample_templates_resources]

#
# Some dot failure with the following templates:
#    https://s3-eu-west-1.amazonaws.com/cloudformation-templates-eu-west-1/EC2InstanceWithEBSVolumeConditionalIOPs.template
#    https://s3-eu-west-1.amazonaws.com/cloudformation-templates-eu-west-1/Parameter_Validate.template
# Known bug in dot:
#    https://gitlab.com/graphviz/graphviz/issues/1213

def main():
    parser = LinkParser()
    for examples_url in EXAMPLES_URLS:
        parser.feed(read_url(examples_url))
        for template in filter(is_template, parser.links):
            render(template)


def is_template(url):
    return urlparse(url).path.endswith('.template')


def render(url):
    template = urlopen(url).read()
    p = subprocess.Popen(
        'cfviz | dot -Tsvg -o %s' % output_for(url), shell=True,
        stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
    output, _ = p.communicate(input=template)
    if output:
        print(url)
        print(output)


def output_for(url):
    name, _ = splitext(basename(urlparse(url).path))
    return f'{OUTPUT_FOLDER}/%s.svg' % name


class LinkParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.links = []

    def handle_starttag(self, tag, attrs):
        if tag == 'a':
            for attr, value in attrs:
                if attr == 'href':
                    self.links.append(value)


def read_url(url):
    return str(urlopen(url).read())


if __name__ == '__main__':
    main()