LAC18 Summary extractor

lac18_ical_filter.py

def ical_import_filter(original, log):
    summary = original.summary
    stuff = summary.split('\n', maxsplit=5)
    # if not(stuff[0].startswith('Author:') and stuff[1].startswith('Type:') and stuff[2].startswith('Topics:') and stuff[3].startswith('Keywords:') and stuff[4].startswith('Abstract')):
    # log(str(summary.replace('\n', '@@@\n')), lvl=hilight)

    data = {
        'author': [],
        'event_type': 'Unknown',
        'event_id': 'Unknown',
        'event_keywords': [],
        'event_topics': [],
        'abstract': ['-'],
        'keywords': "",
        'topics': "",
        'speakers': "",
        'size': 3
    }

    for line in stuff:
        if line.startswith('Author: '):
            authors = line.split('Author: ')[1]
            for author in authors.split('| '):
                data['author'].append(author.split(':')[1].lstrip())
        elif line.startswith('Type: '):
            data['event_type'] = line.split('Type: ')[1]
        elif line.startswith('Topics: '):
            data['event_topics'] = line.split('Topics: ')[1].split(', ')
        elif line.startswith('Keywords: '):
            data['event_keywords'] = line.split('Keywords: ')[1].split(', ')
        elif line.startswith('Abstract: '):
            data['abstract'].append(line.split('Abstract: ')[1])
        elif 'ID: ' in line:
            more_abstract, data['event_id'] = line.split('ID: ', maxsplit=1)
            data['abstract'].append(more_abstract)
        else:
            data['abstract'].append(line)

    data['abstract'] = " ".join(data['abstract']).lstrip("- ")

    if len(data['abstract']) > 100:
        data['size'] = 4
    if len(data['abstract']) > 250:
        data['size'] = 5

    keyword = '<span class="label label-default">%s</span>\n'

    for word in data['event_keywords']:
        data['keywords'] += keyword % word

    for topic in data['event_topics']:
        data['topics'] += keyword % topic

    data['keywords'] = data['keywords'].rstrip('\n')
    data['topics'] = data['topics'].rstrip('\n')

    if len(data['author']) > 1:
        for speaker in data['author']:
            data['speakers'] += " " + speaker + ", "
        data['speakers'] = data['speakers'].rstrip(', ')
    else:
        data['speakers'] = data['author'][0]

    new_summary = """<div class="event_summary">
    <h5> {speakers} - Type: {event_type}""".format(**data)
    if len(data['topics']) > 0:
        new_summary += " - <small>Topics: {topics}</small>".format(**data)
    new_summary += """</h5>\n<h{size}>{abstract}</h{size}>
    <div class="row">
        <div class="col-md-10">
            {keywords}
        </div>
        <div class="col-md-2">
            <small>Talk ID: {event_id}</small>
        </div>
    </div>
</div>
    """.format(**data)

    original.summary = new_summary
    return original

    # 'Author: 1:LAC team\nType: Lightning Talks\nAbstract: A set of lightning talks by you!\nID: 103'