From 835f4eb037f8235991b61fc9742fe0c6e3772e78 Mon Sep 17 00:00:00 2001
From: Jeffrey Serio <hyperreal@moonshadow.dev>
Date: Fri, 6 Dec 2024 16:54:43 -0600
Subject: [PATCH] Use article URL and include Wikinews

---
 README.md           | 28 +++++++++++++++++++++-------
 print_wp_sources.py | 15 ++++++++-------
 pyproject.toml      |  6 +++---
 3 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/README.md b/README.md
index 3bdcacd..b2c15e6 100644
--- a/README.md
+++ b/README.md
@@ -1,19 +1,33 @@
 # print-wp-sources
 
-This program just prints the sources of the given Wikipedia article to standard output.
+This program just prints the sources of the given Wikipedia or Wikinews article to standard output.
 
 ## Installation
 
 ``` shell
-pipx install print-wp-sources --include-deps
+pipx install print-wp-sources
 ```
 
 ## Usage
 
-Use the Wikipedia article's name as the argument to `print-wp-sources`. For example, if the article's URL is `https://en.wikipedia.org/wiki/Automatic_negative_thoughts`, then the argument for `print-wp-sources` would be `"Automatic_negative_thoughts"`.
+Use the Wikipedia or WikiNews article's URL as the argument.
 
 ``` shell
-print-wp-sources "Automatic_negative_thoughts"
+print-wp-sources "https://en.wikinews.org/wiki/Israel-Lebanon_ceasefire_faces_several_violations"
+
+Output:
+https://en.wikinews.org/w/index.php?title=Special:Log&type=review&page=Israel-Lebanon_ceasefire_faces_several_violations
+https://en.wikinews.org/w/index.php?title=Israel-Lebanon_ceasefire_faces_several_violations&action=info#mw-flaggedrevs-action-info-pages-waiting-for-review
+https://thedefensepost.com/2024/12/06/israel-strikes-hezbollah-smuggling-routes/
+https://www.cbsnews.com/news/israel-war-palestinians-ceasefire-hezbollah-lebanon-strained-by-strikes/
+https://www.cbsnews.com/news/israel-hezbollah-ceasefire-claims-of-violations-on-day-2-war-hamas-gaza/
+https://theconversation.com/why-israel-and-hezbollah-reached-a-ceasefire-now-and-what-it-means-for-israel-lebanon-biden-and-trump-244700
+https://www.abc.net.au/news/2024-11-25/lebanon-ceasefire-pending-israeli-response/104642856
+https://www.aljazeera.com/news/liveblog/2024/11/25/live-destruction-in-tel-aviv-beirut-amid-hezbollah-israel-missile-fire
+```
+
+```shell
+print-wp-sources "https://en.wikipedia.org/wiki/Automatic_negative_thoughts"
 
 Output:
 https://pubmed.ncbi.nlm.nih.gov/26431418
@@ -27,11 +41,11 @@ https://pubmed.ncbi.nlm.nih.gov/6630686
 https://wikimediafoundation.org/
 ```
 
-> Note: make sure to use quotes around the article name in the argument to `print-wp-sources`.
+> Note: make sure to use quotes around the article URL in the argument to `print-wp-sources`.
 
 One can also easily pipe the output to a file.
 
 ``` shell
-print-wp-sources "Automatic_negative_thoughts" > sources.txt
-print-wp-sources "Python_(programming_language)" | tee sources.txt
+print-wp-sources "https://en.wikipedia.org/wiki/Automatic_negative_thoughts" > sources.txt
+print-wp-sources "https://en.wikipedia.org/wiki/Python_(programming_language)" | tee sources.txt
 ```
diff --git a/print_wp_sources.py b/print_wp_sources.py
index cfe6d3e..efb9e71 100644
--- a/print_wp_sources.py
+++ b/print_wp_sources.py
@@ -1,20 +1,21 @@
 import sys
-from urllib.parse import unquote
-from urllib.request import urlopen
 
+import requests
 from bs4 import BeautifulSoup
 
 
 def main():
     if len(sys.argv) != 2:
-        exit("Usage: print-wp-sources ARTICLE_NAME")
-    article = sys.argv[1]
+        exit("Usage: print-wp-sources ARTICLE_URL")
+    article_url = sys.argv[1]
 
-    url = f"https://en.wikipedia.org/wiki/{article}"
-    text = urlopen(url).read()
+    text = requests.get(article_url).text
     soup = BeautifulSoup(text, "html.parser")
     for link in soup.find_all("a", attrs={"class": "external text"}):
-        print(unquote(link.get("href")))
+        if "wikimediafoundation.org" not in link.get(
+            "href"
+        ) and "foundation.wikimedia.org" not in link.get("href"):
+            print(link.get("href"))
 
 
 if __name__ == "__main__":
diff --git a/pyproject.toml b/pyproject.toml
index 26c5818..055b258 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,10 +1,10 @@
 [project]
 name = "print-wp-sources"
-version = "0.4"
+version = "0.5"
 authors = [
   { name="Jeffrey Serio", email="hyperreal@fedoraproject.org" },
 ]
-description = "Print sources from Wikipedia articles to stdout."
+description = "Print sources from Wikipedia or Wikinews articles to stdout."
 readme = "README.md"
 requires-python = ">=3.10"
 classifiers = [
@@ -12,7 +12,7 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
     "Operating System :: OS Independent",
 ]
-dependencies = ["beautifulsoup4>=4.12.3"]
+dependencies = ["beautifulsoup4>=4.12.3", "requests>=2.32.3"]
 
 [project.scripts]
 print-wp-sources = "print_wp_sources:main"