From 65a19f4c5fdeea6b4afa12d138f9319a063d618f Mon Sep 17 00:00:00 2001
From: Yves Fischer <yvesf-git@xapek.org>
Date: Fri, 9 Dec 2016 21:19:19 +0100
Subject: add --test to test newspaper3k text extraction

---
 watchnews/fetch.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'watchnews')

diff --git a/watchnews/fetch.py b/watchnews/fetch.py
index e6c5c39..c476be7 100755
--- a/watchnews/fetch.py
+++ b/watchnews/fetch.py
@@ -8,6 +8,20 @@ from newspaper.cleaners import DocumentCleaner
 
 import logging
 
+def dump_paper(link):
+    paper = Article(link)
+    paper.download()
+    paper.parse()
+    print("""\
+Article Dump:
+Title: {title}
+Url: {url}
+Authors: {authors}
+Text: {text}
+-----
+
+""".format(**paper.__dict__))
+
 def update(feed):
     logging.info('Update %s', feed.url)
     result = feedparser.parse(feed.url)
-- 
cgit v1.2.1