parse.py 文件源码

def parse_pocket_export(html_file):
    """Parse Pocket-format bookmarks export files (produced by getpocket.com/export/)"""

    html_file.seek(0)
    pattern = re.compile("^\\s*<li><a href=\"(.+)\" time_added=\"(\\d+)\" tags=\"(.*)\">(.+)</a></li>", re.UNICODE)
    for line in html_file:
        # example line
        # <li><a href="http://example.com/ time_added="1478739709" tags="tag1,tag2">example title</a></li>
        match = pattern.search(line)
        if match:
            fixed_url = match.group(1).replace('http://www.readability.com/read?url=', '')           # remove old readability prefixes to get original url
            time = datetime.fromtimestamp(float(match.group(2)))
            info = {
                'url': fixed_url,
                'domain': domain(fixed_url),
                'base_url': base_url(fixed_url),
                'timestamp': str(time.timestamp()),
                'tags': match.group(3),
                'title': match.group(4).replace(' — Readability', '').replace('http://www.readability.com/read?url=', '') or base_url(fixed_url),
                'sources': [html_file.name],
            }
            info['type'] = get_link_type(info)
            yield info