add --test to test newspaper3k text extractionHEADmaster

1 files changed, 14 insertions, 0 deletions

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)