From 9f0acb950d9c85b5701760ecf7aafbfe3374341c Mon Sep 17 00:00:00 2001
From: Mark Powers <mark@marks.kitchen>
Date: Sat, 5 Sep 2020 01:59:22 +0000
Subject: Add archive.org link handling

---
 main.py | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 main.py

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..28d4086
--- /dev/null
+++ b/main.py
@@ -0,0 +1,55 @@
+from bs4 import BeautifulSoup
+from datetime import date
+from mastodon import Mastodon
+
+import sys
+import requests
+import datetime
+import json
+
+base_url = "https://news.ycombinator.com/"
+year = int(date.today().strftime("%Y")) - 10
+today = str(year) + date.today().strftime("-%m-%d")
+r = requests.get('https://news.ycombinator.com/front?day='+today)
+soup = BeautifulSoup(r.text, features="lxml")
+items = soup.find_all("tr", "athing")[:3]
+
+index = int(sys.argv[1])
+item = items[index]
+
+story = item.find("a", "storylink")
+title = story.text
+link = story["href"]
+if "http" not in link:
+    link = base_url + link
+try:
+    r = requests.get(link)
+    if r.status_code == 404:
+        raise Exception(404)
+except:
+    timestamp = int(datetime.datetime.timestamp(datetime.datetime.today() - datetime.timedelta(days=(10 * 365))))
+    r = requests.get("http://archive.org/wayback/available?url=" + link + "&timestamp=" + str(timestamp))
+    res = r.json()
+    if res["archived_snapshots"] and res["archived_snapshots"]["closest"]["available"]:
+        link = res["archived_snapshots"]["closest"]["url"]
+    else:
+        link = "[dead link]"
+
+    
+
+
+comment_el = item.next_sibling
+comment_link = base_url + comment_el.find_all("a")[-1]["href"]
+if comment_link == link:
+    comment_link = ""
+
+toot_content = title + "\n" + link + "\n"+comment_link
+
+mastodon = Mastodon(
+    access_token = '/home/mark/hndecade/hndecade_usercred.secret',
+    api_base_url = 'https://botsin.space'
+)
+
+print(toot_content)
+#mastodon.toot(toot_content)
+
-- 
cgit v1.2.3