Added an option to choose if URL of articles behind proxies should be resolved.

3 files changed, 13 insertions, 10 deletions

diff --git a/conf.py b/conf.py
index 3f406477..3b723f76 100644
--- a/conf.py
+++ b/conf.py
@@ -25,6 +25,7 @@ DATABASE_ADDRESS = config.get('database', 'address')
 
 HTTP_PROXY = config.get('feedparser', 'http_proxy')
 USER_AGENT = config.get('feedparser', 'user_agent')
+RESOLVE_ARTICLE_URL = int(config.get('feedparser', 'resolve_article_url')) == 1
 
 WEBSERVER_DEBUG = int(config.get('webserver', 'debug')) == 1
 WEBSERVER_HOST = config.get('webserver', 'host')
diff --git a/conf/conf.cfg-sample b/conf/conf.cfg-sample
index 07027bfd..3ed7a1b1 100644
--- a/conf/conf.cfg-sample
+++ b/conf/conf.cfg-sample
@@ -7,6 +7,7 @@ password = root
 [feedparser]
 http_proxy = 
 user_agent = pyAggr3g470r (https://bitbucket.org/cedricbonhomme/pyaggr3g470r)
+resolve_article_url = 0
 [webserver]
 debug = 1
 host = 0.0.0.0
diff --git a/pyaggr3g470r/feedgetter.py b/pyaggr3g470r/feedgetter.py
index 3b77509f..d29d3c9e 100644
--- a/pyaggr3g470r/feedgetter.py
+++ b/pyaggr3g470r/feedgetter.py
@@ -110,16 +110,17 @@ class FeedGetter(object):
         for article in a_feed['entries']:
 
             nice_url = article.link.encode("utf-8")
-            try:
-                # resolves URL behind proxies (like feedproxy.google.com)
-                r = requests.get(article.link, timeout=5.0, proxies=self.proxies)
-                nice_url = r.url.encode("utf-8")
-            except Timeout:
-                pyaggr3g470r_log.warning("Timeout when getting the real URL of %s." % (article.link,))
-                continue
-            except Exception as e:
-                pyaggr3g470r_log.warning("Unable to get the real URL of %s. Error: %s" % (article.link, str(e)))
-                continue
+            if conf.RESOLVE_ARTICLE_URL:
+                try:
+                    # resolves URL behind proxies (like feedproxy.google.com)
+                    r = requests.get(article.link, timeout=5.0, proxies=self.proxies)
+                    nice_url = r.url.encode("utf-8")
+                except Timeout:
+                    pyaggr3g470r_log.warning("Timeout when getting the real URL of %s." % (article.link,))
+                    continue
+                except Exception as e:
+                    pyaggr3g470r_log.warning("Unable to get the real URL of %s. Error: %s" % (article.link, str(e)))
+                    continue
             # remove utm_* parameters
             parsed_url = urlparse(nice_url)
             qd = parse_qs(parsed_url.query, keep_blank_values=True)