# characters, we iterate through the list below and use the
# first character set that works.
('encodings', 'US-ASCII, ISO-8859-1, UTF-8, BIG5, ISO-2022-JP'),
+ # True: Use RFC 2392's cid: to include and link referenced data.
+ # False: Only include the converted entry, not its references.
+ ('include-references', str(False)),
## HTML conversion
# True: Send text/html messages when possible.
# False: Convert HTML to plain text.
"""
import collections as _collections
+from email.mime.multipart import MIMEMultipart as _MIMEMultipart
+from email.mime.nonmultipart import MIMENonMultipart as _MIMENonMultipart
from email.utils import formataddr as _formataddr
import hashlib as _hashlib
import html as _html
import socket as _socket
import time as _time
import urllib.error as _urllib_error
+import urllib.parse as _urllib_parse
import urllib.request as _urllib_request
import xml.sax as _sax
'active',
'date_header',
'trust_guid',
+ 'include_references',
'html_mail',
'use_css',
'unicode_snob',
content = self._get_entry_content(entry)
try:
- content = self._process_entry_content(
+ parts = self._process_entry_content(
entry=entry, content=content, subject=subject)
except _error.ProcessingError as e:
e.parsed = parsed
raise
- message = _email.get_message(
+ if len(parts) == 1:
+ message = parts[0]
+ else:
+ _MIMEMultipart()
+ for part in parts:
+ message.attach(part)
+ _email.set_headers(
+ message=message,
sender=sender,
recipient=self.to,
subject=subject,
- body=content['value'],
- content_type=content['type'].split('/', 1)[1],
extra_headers=extra_headers,
config=self.config,
section=self.section)
return {'type': 'text/plain', 'value': ''}
def _process_entry_content(self, entry, content, subject):
- "Convert entry content to the requested format."
+ """Convert entry content to the requested format
+
+ Returns a list of parts, with a `text/*` part first containing
+ the content. If `self.include_references` is True, the
+ referenced parts are also included as attachments.
+ """
+ parts = []
link = self._get_entry_link(entry)
+ if content['type'] in ('text/html', 'application/xhtml+xml'):
+ html_content,new_parts = self._process_entry_content_html(
+ entry=entry, content=content, subject=subject,
+ html=content['value'].strip())
+ parts.extend(new_parts)
+ else:
+ html_content = _html.escape(content['value'].strip())
if self.html_mail:
lines = [
'<!DOCTYPE html>',
'<p>URL: <a href="{0}">{0}</a></p>'.format(link),
])
for enclosure in getattr(entry, 'enclosures', []):
+ part = None
if getattr(enclosure, 'url', None):
+ ref_link,part = self._get_reference(url=enclosure.url)
lines.append(
'<p>Enclosure: <a href="{0}">{0}</a></p>'.format(
- enclosure.url))
+ ref_link))
if getattr(enclosure, 'src', None):
+ ref_link,part = self._get_reference(url=enclosure.src)
lines.append(
'<p>Enclosure: <a href="{0}">{0}</a></p>'.format(
- enclosure.src))
- lines.append(
- '<p><img src="{}" /></p>'.format(enclosure.src))
+ ref_link))
+ lines.append('<p><img src="{}" /></p>'.format(ref_link))
+ if part:
+ parts.append(part)
for elink in getattr(entry, 'links', []):
+ part = None
if elink.get('rel', None) == 'via':
url = elink['href']
+ ref_link,part = self._get_reference(url=url)
title = elink.get('title', url)
lines.append('<p>Via <a href="{}">{}</a></p>'.format(
- url, title))
+ ref_link, title))
+ if part:
+ parts.append(part)
lines.extend([
'</div>', # /footer
'</div>', # /entry
''])
content['type'] = 'text/html'
content['value'] = '\n'.join(lines)
- return content
else: # not self.html_mail
if content['type'] in ('text/html', 'application/xhtml+xml'):
try:
lines.append('')
lines.append('URL: {}'.format(link))
for enclosure in getattr(entry, 'enclosures', []):
- if getattr(enclosure, 'url', None):
- lines.append('Enclosure: {}'.format(enclosure.url))
- if getattr(enclosure, 'src', None):
- lines.append('Enclosure: {}'.format(enclosure.src))
+ for url in [
+ getattr(enclosure, 'url', None),
+ getattr(enclosure, 'src', None),
+ ]:
+ ref_link,part = self._get_reference(url=url)
+ lines.append('Enclosure: {}'.format(ref_link))
+ if part:
+ parts.append(part)
for elink in getattr(entry, 'links', []):
if elink.get('rel', None) == 'via':
url = elink['href']
+ ref_link,part = self._get_reference(url=url)
title = elink.get('title', url)
- lines.append('Via: {} {}'.format(title, url))
+ lines.append('Via: {} {}'.format(title, ref_link))
+ if part:
+ parts.append(part)
content['type'] = 'text/plain'
content['value'] = '\n'.join(lines)
- return content
+ content_part = _email.get_mimetext(
+ body=content['value'],
+ content_type=content['type'].split('/', 1)[1],
+ config=self.config,
+ section=self.section)
+ parts.insert(0, content_part)
+ return parts
+
+ def _process_entry_content_html(self, entry, content, subject, html):
+ """Manipulate the entry HTML
+
+ For example, replace links to images with cid: links if
+ `self.include_references` is True.
+
+ Returns a the new HTML and a list of parts (which may be empty).
+ """
+ return (html, []) # TODO
+
+ def _get_reference(self, url):
+ """Get references for cid: links.
+
+ RFC 2392 [1] provides linking between message parts based on
+ Content-IDs via `cid:...` URLs. If `self.include_references`
+ is True, download the object referenced by `url` and return a
+ tuple containing a `cid:...` URL and the MIME part containing
+ the referenced data. Otherwise, return `(url, None)`.
+
+ [1]: http://tools.ietf.org/html/rfc2392
+ """
+ if self.include_references:
+ cid = _email.get_id()
+ link = 'cid:{}'.format(_urllib_parse.quote(cid[1:-1]))
+ _LOG.critical(link)
+ part = _MIMENoneMultipart('image', 'png')
+ part.add_content(b'AAA')
+ else:
+ link = url
+ part = None
+ _LOG.critical((link, part))
+ return (link, part)
def _send(self, sender, message):
_LOG.info('send message for {}'.format(self))
--- /dev/null
+[DEFAULT]
+to = a@b.com
+date-header = True
--- /dev/null
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Flowchart
+Date: Fri, 05 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1195/
+X-RSS-URL: http://xkcd.com/1195/
+
+
+
+
+
+URL: http://xkcd.com/1195/
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Subways
+Date: Mon, 08 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1196/
+X-RSS-URL: http://xkcd.com/1196/
+
+
+
+
+
+URL: http://xkcd.com/1196/
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: All Adobe Updates
+Date: Wed, 10 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1197/
+X-RSS-URL: http://xkcd.com/1197/
+
+
+
+
+
+URL: http://xkcd.com/1197/
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Geologist
+Date: Fri, 12 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1198/
+X-RSS-URL: http://xkcd.com/1198/
+
+
+
+
+
+URL: http://xkcd.com/1198/
--- /dev/null
+[DEFAULT]
+to = a@b.com
+date-header = True
+html-mail = True
--- /dev/null
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/html; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Flowchart
+Date: Fri, 05 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1195/
+X-RSS-URL: http://xkcd.com/1195/
+
+<!DOCTYPE html>
+<html>
+ <head>
+</head>
+<body>
+<div id="entry>
+<h1 class="header"><a href="http://xkcd.com/1195/">Flowchart</a></h1>
+<div id="body">
+<img alt="The way out is to use the marker you have to add a box that says 'get a marker' to the line between you and 'start', then add a 'no' line from the trap box to 'end'." src="http://imgs.xkcd.com/comics/flowchart.png" title="The way out is to use the marker you have to add a box that says 'get a marker' to the line between you and 'start', then add a 'no' line from the trap box to 'end'." />
+</div>
+<div class="footer"><p>URL: <a href="http://xkcd.com/1195/">http://xkcd.com/1195/</a></p>
+</div>
+</div>
+</body>
+</html>
+
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/html; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Subways
+Date: Mon, 08 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1196/
+X-RSS-URL: http://xkcd.com/1196/
+
+<!DOCTYPE html>
+<html>
+ <head>
+</head>
+<body>
+<div id="entry>
+<h1 class="header"><a href="http://xkcd.com/1196/">Subways</a></h1>
+<div id="body">
+<img alt="About one in three North American subway stops are in NYC." src="http://imgs.xkcd.com/comics/subways.png" title="About one in three North American subway stops are in NYC." />
+</div>
+<div class="footer"><p>URL: <a href="http://xkcd.com/1196/">http://xkcd.com/1196/</a></p>
+</div>
+</div>
+</body>
+</html>
+
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/html; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: All Adobe Updates
+Date: Wed, 10 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1197/
+X-RSS-URL: http://xkcd.com/1197/
+
+<!DOCTYPE html>
+<html>
+ <head>
+</head>
+<body>
+<div id="entry>
+<h1 class="header"><a href="http://xkcd.com/1197/">All Adobe Updates</a></h1>
+<div id="body">
+<img alt="ALERT: Some pending mandatory software updates require version 21.1.2 of the Oracle/Sun Java(tm) JDK(tm) Update Manager Runtime Environment Meta-Updater, which is not available for your platform." src="http://imgs.xkcd.com/comics/all_adobe_updates.png" title="ALERT: Some pending mandatory software updates require version 21.1.2 of the Oracle/Sun Java(tm) JDK(tm) Update Manager Runtime Environment Meta-Updater, which is not available for your platform." />
+</div>
+<div class="footer"><p>URL: <a href="http://xkcd.com/1197/">http://xkcd.com/1197/</a></p>
+</div>
+</div>
+</body>
+</html>
+
+
+SENT BY: "xkcd.com" <user@rss2email.invalid>
+MIME-Version: 1.0
+Content-Type: text/html; charset="us-ascii"
+Content-Transfer-Encoding: 7bit
+From: "xkcd.com" <user@rss2email.invalid>
+To: a@b.com
+Subject: Geologist
+Date: Fri, 12 Apr 2013 00:00:00 -0000
+Message-ID: <...@dev.null.invalid>
+User-Agent: rss2email
+X-RSS-Feed: xkcd/feed.atom
+X-RSS-ID: http://xkcd.com/1198/
+X-RSS-URL: http://xkcd.com/1198/
+
+<!DOCTYPE html>
+<html>
+ <head>
+</head>
+<body>
+<div id="entry>
+<h1 class="header"><a href="http://xkcd.com/1198/">Geologist</a></h1>
+<div id="body">
+<img alt="'It seems like it's still alive, Professor.' 'Yeah, a big one like this can keep running around for a few billion years after you remove the head."" src="http://imgs.xkcd.com/comics/geologist.png" title="'It seems like it's still alive, Professor.' 'Yeah, a big one like this can keep running around for a few billion years after you remove the head."" />
+</div>
+<div class="footer"><p>URL: <a href="http://xkcd.com/1198/">http://xkcd.com/1198/</a></p>
+</div>
+</div>
+</body>
+</html>
+
--- /dev/null
+[DEFAULT]
+to = a@b.com
+date-header = True
+include-references = True
--- /dev/null
+[DEFAULT]
+to = a@b.com
+date-header = True
+include-references = True
+html-mail = True
--- /dev/null
+feed.atom is a snapshot of
+
+ http://xkcd.com/atom.xml
+
+as of 2013-04-14.
+
+HTTP headers:
+
+ HTTP/1.1 200 OK
+ Vary: Accept-Encoding
+ Content-Type: application/xml
+ Accept-Ranges: bytes
+ ETag: "3353825625"
+ Last-Modified: Fri, 12 Apr 2013 04:00:05 GMT
+ Content-Length: 2498
+ Date: Sun, 14 Apr 2013 12:49:47 GMT
+ Server: lighttpd/1.4.28
+
+The URLs referenced from the entries were downloaded on the same day
+and stored with filenames matching their URL
+(e.g. `http://imgs.xkcd.com/comics/geologist.png` is stored as
+`imgs.xkcd.com/comics/geologist.png`).
--- /dev/null
+<?xml version="1.0" encoding="utf-8"?>
+<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en"><title>xkcd.com</title><link href="http://xkcd.com/" rel="alternate"></link><id>http://xkcd.com/</id><updated>2013-04-12T00:00:00Z</updated><entry><title>Geologist</title><link href="http://xkcd.com/1198/" rel="alternate"></link><updated>2013-04-12T00:00:00Z</updated><id>http://xkcd.com/1198/</id><summary type="html"><img src="http://imgs.xkcd.com/comics/geologist.png" title="'It seems like it's still alive, Professor.' 'Yeah, a big one like this can keep running around for a few billion years after you remove the head.&quot;" alt="'It seems like it's still alive, Professor.' 'Yeah, a big one like this can keep running around for a few billion years after you remove the head.&quot;" /></summary></entry><entry><title>All Adobe Updates</title><link href="http://xkcd.com/1197/" rel="alternate"></link><updated>2013-04-10T00:00:00Z</updated><id>http://xkcd.com/1197/</id><summary type="html"><img src="http://imgs.xkcd.com/comics/all_adobe_updates.png" title="ALERT: Some pending mandatory software updates require version 21.1.2 of the Oracle/Sun Java(tm) JDK(tm) Update Manager Runtime Environment Meta-Updater, which is not available for your platform." alt="ALERT: Some pending mandatory software updates require version 21.1.2 of the Oracle/Sun Java(tm) JDK(tm) Update Manager Runtime Environment Meta-Updater, which is not available for your platform." /></summary></entry><entry><title>Subways</title><link href="http://xkcd.com/1196/" rel="alternate"></link><updated>2013-04-08T00:00:00Z</updated><id>http://xkcd.com/1196/</id><summary type="html"><img src="http://imgs.xkcd.com/comics/subways.png" title="About one in three North American subway stops are in NYC." alt="About one in three North American subway stops are in NYC." /></summary></entry><entry><title>Flowchart</title><link href="http://xkcd.com/1195/" rel="alternate"></link><updated>2013-04-05T00:00:00Z</updated><id>http://xkcd.com/1195/</id><summary type="html"><img src="http://imgs.xkcd.com/comics/flowchart.png" title="The way out is to use the marker you have to add a box that says 'get a marker' to the line between you and 'start', then add a 'no' line from the trap box to 'end'." alt="The way out is to use the marker you have to add a box that says 'get a marker' to the line between you and 'start', then add a 'no' line from the trap box to 'end'." /></summary></entry></feed>
\ No newline at end of file
projects / rss2email.git / commitdiff
