tAllow relative URIs in article linkes. - zs - Zeitungsschau rss to email converter
(HTM) git clone git://r-36.net/zs
(DIR) Log
(DIR) Files
(DIR) Refs
(DIR) LICENSE
---
(DIR) commit 86b129e4386789f5331765d7b96098e6c2c7bde7
(DIR) parent 4010b280ba3871965b852aad19c26f9331e861bd
(HTM) Author: Christoph Lohmann <20h@r-36.net>
Date: Sun, 15 Apr 2018 11:35:39 +0200
Allow relative URIs in article linkes.
+ Add feeduri for better filtering handling.
Diffstat:
zeitungsschau/feed.py | 11 ++++++++---
zeitungsschau/feeddb.py | 4 ++--
zeitungsschau/feedemail.py | 21 ++++++++++++++++++++-
3 files changed, 30 insertions(+), 6 deletions(-)
---
(DIR) diff --git a/zeitungsschau/feed.py b/zeitungsschau/feed.py
t@@ -414,9 +414,14 @@ def fetch(uri):
ftype = "twtxt"
if ftype == "xml":
- return (rcode, parseatomfeed(fval))
+ rval = (rcode, parseatomfeed(fval))
elif ftype == "twtxt":
- return (rcode, parsetwtxtfeed(fval.decode("utf-8"), uri))
+ rval = (rcode, parsetwtxtfeed(fval.decode("utf-8"), uri))
else:
- return (rcode, parsejsonfeed(fval.decode("utf-8")))
+ rval = (rcode, parsejsonfeed(fval.decode("utf-8")))
+
+ if rval[1] != None:
+ rval[1]["feeduri"] = uri
+
+ return rval
(DIR) diff --git a/zeitungsschau/feeddb.py b/zeitungsschau/feeddb.py
t@@ -215,7 +215,7 @@ class feeddb(object):
feed["articles"] = history[-2048:]
for metakey in ("link", "title", "updated", "author", \
- "email"):
+ "email", "feeduri"):
if metakey in curfeed:
feed[metakey] = curfeed[metakey]
t@@ -232,7 +232,7 @@ class feeddb(object):
return rfeed
for metakey in ("link", "title", "updated", "author", \
- "email", "toemail"):
+ "email", "toemail", "feeduri"):
if metakey in feed:
rfeed[metakey] = feed[metakey]
(DIR) diff --git a/zeitungsschau/feedemail.py b/zeitungsschau/feedemail.py
t@@ -13,6 +13,7 @@ from email.header import Header
import time
import subprocess
import lxml.html
+import urllib.parse
import html2text
t@@ -96,9 +97,27 @@ def send(feed, to, smtphost="localhost", smtpport=None, ssl="False",\
msg["Subject"] = subject
if "link" in article:
- msg["X-RSS-URL"] = article["link"]
+ if "://" not in article["link"]:
+ aurl = urllib.parse.urljoin(feed["feeduri"],\
+ article["link"])
+ if "gopher://" in aurl:
+ urls = urllib.parse.urlparse(aurl, \
+ allow_fragments=False)
+ if urls.path.startswith("/0"):
+ aurl = "%s://%s%s" % \
+ (urls.scheme, urls.netloc, \
+ urls.path.replace(\
+ "/0", "/1", 1))
+ if len(urls.query) > 0:
+ aurl = "%s?%s" % \
+ (aurl, urls.query)
+ else:
+ aurl = article["link"]
+ msg["X-RSS-URL"] = aurl
if "link" in feed:
msg["X-RSS-Feed"] = feed["link"]
+ else:
+ msg["X-RSS-Feed"] = feed["feeduri"]
if "id" in article:
msg["X-RSS-ID"] = article["id"]
if "uuid" in article: