def parse_rss_export(rss_file):
"""Parse RSS XML-format files into links"""
rss_file.seek(0)
items = rss_file.read().split('</item>\n<item>')
for item in items:
# example item:
# <item>
# <title><![CDATA[How JavaScript works: inside the V8 engine]]></title>
# <category>Unread</category>
# <link>https://blog.sessionstack.com/how-javascript-works-inside</link>
# <guid>https://blog.sessionstack.com/how-javascript-works-inside</guid>
# <pubDate>Mon, 21 Aug 2017 14:21:58 -0500</pubDate>
# </item>
trailing_removed = item.split('</item>', 1)[0]
leading_removed = trailing_removed.split('<item>', 1)[-1]
rows = leading_removed.split('\n')
def get_row(key):
return [r for r in rows if r.startswith('<{}>'.format(key))][0]
title = str_between(get_row('title'), '<![CDATA[', ']]')
url = str_between(get_row('link'), '<link>', '</link>')
ts_str = str_between(get_row('pubDate'), '<pubDate>', '</pubDate>')
time = datetime.strptime(ts_str, "%a, %d %b %Y %H:%M:%S %z")
info = basic_link_info(url, rss_file, title, time)
yield info
def parse_shaarli_rss_export(rss_file):
"""Parse Shaarli-specific RSS XML-format files into links"""
rss_file.seek(0)
entries = rss_file.read().split('<entry>')[1:]
for entry in entries:
# example entry:
# <entry>
# <title>Aktuelle Trojaner-Welle: Emotet lauert in gefälschten Rechnungsmails | heise online</title>
# <link href="https://www.heise.de/security/meldung/Aktuelle-Trojaner-Welle-Emotet-lauert-in-gefaelschten-Rechnungsmails-4291268.html" />
# <id>https://demo.shaarli.org/?cEV4vw</id>
# <published>2019-01-30T06:06:01+00:00</published>
# <updated>2019-01-30T06:06:01+00:00</updated>
# <content type="html" xml:lang="en"><![CDATA[<div class="markdown"><p>— <a href="https://demo.shaarli.org/?cEV4vw">Permalink</a></p></div>]]></content>
# </entry>
trailing_removed = entry.split('</entry>', 1)[0]
leading_removed = trailing_removed.strip()
rows = leading_removed.split('\n')
def get_row(key):
return [r.strip() for r in rows if r.strip().startswith('<{}'.format(key))][0]
title = str_between(get_row('title'), '<title>', '</title>').strip()
url = str_between(get_row('link'), '<link href="', '" />')
ts_str = str_between(get_row('published'), '<published>', '</published>')
time = datetime.strptime(ts_str, "%Y-%m-%dT%H:%M:%S%z")
yield {
'url': url,
'timestamp': str(time.timestamp()),
'title': title or None,
'tags': '',
'sources': [rss_file.name],
}
def parse_rss_export(rss_file):
"""Parse RSS XML-format files into links"""
rss_file.seek(0)
items = rss_file.read().split('</item>\n<item>')
for item in items:
# example item:
# <item>
# <title><![CDATA[How JavaScript works: inside the V8 engine]]></title>
# <category>Unread</category>
# <link>https://blog.sessionstack.com/how-javascript-works-inside</link>
# <guid>https://blog.sessionstack.com/how-javascript-works-inside</guid>
# <pubDate>Mon, 21 Aug 2017 14:21:58 -0500</pubDate>
# </item>
trailing_removed = item.split('</item>', 1)[0]
leading_removed = trailing_removed.split('<item>', 1)[-1]
rows = leading_removed.split('\n')
def get_row(key):
return [
r for r in rows if r.strip().startswith('<{}>'.format(key))
][0]
title = str_between(get_row('title'), '<![CDATA[', ']]').strip()
url = str_between(get_row('link'), '<link>', '</link>')
ts_str = str_between(get_row('pubDate'), '<pubDate>', '</pubDate>')
time = datetime.strptime(ts_str, "%a, %d %b %Y %H:%M:%S %z")
info = {
'url': url,
'domain': domain(url),
'base_url': base_url(url),
'timestamp': str(time.timestamp()),
'tags': '',
'title': title or fetch_page_title(url),
'sources': [rss_file.name],
}
info['type'] = get_link_type(info)
yield info
