From b5c6d34860d1303c696867de12750deac65eb757 Mon Sep 17 00:00:00 2001
From: Chris Dzombak <chris@chrisdzombak.net>
Date: Tue, 13 Mar 2018 21:11:11 -0400
Subject: [PATCH 1/3] Add support for Pinboard RSS feeds

---
 parse.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/parse.py b/parse.py
index d5eda177..afa31341 100644
--- a/parse.py
+++ b/parse.py
@@ -17,6 +17,7 @@ Parsed link schema: {
 
 import re
 import json
+import xml.etree.ElementTree as etree
 
 from datetime import datetime
 
@@ -36,6 +37,7 @@ def get_parsers(file):
         'pinboard': parse_json_export,
         'bookmarks': parse_bookmarks_export,
         'rss': parse_rss_export,
+        'pinboard_rss': parse_pinboard_rss_feed,
     }
 
 def parse_links(path):
@@ -169,3 +171,31 @@ def parse_bookmarks_export(html_file):
             info['type'] = get_link_type(info)
 
             yield info
+
+def parse_pinboard_rss_feed(rss_file):
+    """Parse Pinboard RSS feed files into links"""
+
+    rss_file.seek(0)
+    root = etree.parse(rss_file).getroot()
+    items = root.findall("{http://purl.org/rss/1.0/}item")
+    for item in items:
+        url = item.find("{http://purl.org/rss/1.0/}link").text
+        tags = item.find("{http://purl.org/dc/elements/1.1/}subject").text
+        title = item.find("{http://purl.org/rss/1.0/}title").text
+        ts_str = item.find("{http://purl.org/dc/elements/1.1/}date").text
+        # Pinboard includes a colon in its date stamp timezone offsets, which
+        # Python can't parse. Remove it:
+        if ":" == ts_str[-3:-2]:
+            ts_str = ts_str[:-3]+ts_str[-2:]
+        time = datetime.strptime(ts_str, "%Y-%m-%dT%H:%M:%S%z")
+        info = {
+            'url': url,
+            'domain': domain(url),
+            'base_url': base_url(url),
+            'timestamp': str(time.timestamp()),
+            'tags': tags,
+            'title': title,
+            'sources': [rss_file.name],
+        }
+        info['type'] = get_link_type(info)
+        yield info

From f49f1b5aa07fa5036e8e5a7c1443b4fecfec1e45 Mon Sep 17 00:00:00 2001
From: Chris Dzombak <chris@chrisdzombak.net>
Date: Tue, 13 Mar 2018 22:23:52 -0400
Subject: [PATCH 2/3] Parse Medium RSS feeds

closes https://github.com/pirate/bookmark-archiver/issues/64
---
 parse.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/parse.py b/parse.py
index afa31341..442efc2d 100644
--- a/parse.py
+++ b/parse.py
@@ -38,6 +38,7 @@ def get_parsers(file):
         'bookmarks': parse_bookmarks_export,
         'rss': parse_rss_export,
         'pinboard_rss': parse_pinboard_rss_feed,
+        'medium_rss': parse_medium_rss_feed,
     }
 
 def parse_links(path):
@@ -199,3 +200,28 @@ def parse_pinboard_rss_feed(rss_file):
         }
         info['type'] = get_link_type(info)
         yield info
+
+def parse_medium_rss_feed(rss_file):
+    """Parse Medium RSS feed files into links"""
+
+    rss_file.seek(0)
+    root = etree.parse(rss_file).getroot()
+    items = root.find("channel").findall("item")
+    for item in items:
+        for child in item:
+            print(child.tag, child.text)
+        url = item.find("link").text
+        title = item.find("title").text
+        ts_str = item.find("pubDate").text
+        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,
+            'sources': [rss_file.name],
+        }
+        info['type'] = get_link_type(info)
+        yield info

From 0012742d04d5ebb08aa77464e6ffae3be5499235 Mon Sep 17 00:00:00 2001
From: Chris Dzombak <chris@chrisdzombak.net>
Date: Wed, 14 Mar 2018 17:38:39 -0400
Subject: [PATCH 3/3] =?UTF-8?q?Treat=20ParseError=20as=20an=20indication?=
 =?UTF-8?q?=20that=20a=20parser=20doesn=E2=80=99t=20apply=20to=20the=20inp?=
 =?UTF-8?q?ut=20file?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 parse.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/parse.py b/parse.py
index 442efc2d..49fe201c 100644
--- a/parse.py
+++ b/parse.py
@@ -52,7 +52,7 @@ def parse_links(path):
                 links += list(parser_func(file))
                 if links:
                     break
-            except (ValueError, TypeError, IndexError):
+            except (ValueError, TypeError, IndexError, etree.ParseError):
                 # parser not supported on this file
                 pass