attempt at multi URL downloads

modules/papers.py

@@ -1,7 +1,7 @@
 """
 Fetches papers.
 """
-
+import re
 import os
 import json
 import random
@@ -39,7 +39,7 @@ def download(phenny, input, verbose=True):
     # don't bother if there's nothing there
     if len(line) < 5 or (not "http://" in line and not "https://" in line) or not line.startswith("http"):
         return
-
+	for line in re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line):
 		translation_url = "http://localhost:1969/web"
 
 		headers = {
@@ -84,10 +84,10 @@ def download(phenny, input, verbose=True):
 					# detect failure
 					if response.status_code == 401:
 						phenny.say("HTTP 401 unauthorized " + str(pdf_url))
-                    return
+						continue
 					elif response.status_code != 200:
 						phenny.say("HTTP " + str(response.status_code) + " " + str(pdf_url))
-                    return
+						continue
 
 					data = response.content
 
@@ -104,25 +104,26 @@ def download(phenny, input, verbose=True):
 					url = "http://diyhpl.us/~bryan/papers2/paperbot/" + filename + ".pdf"
 
 					phenny.say(url)
-                return
+					continue
 				elif verbose and explicit:
 					phenny.say("error: didn't find any pdfs on " + line)
 					phenny.say(download_url(line))
-                return
+					continue
 			elif verbose and explicit:
 				phenny.say("error: dunno how to find the pdf on " + line)
 				phenny.say(download_url(line))
-            return
+				continue
 		elif verbose and explicit:
 			if response.status_code == 501:
 				if verbose:
 					phenny.say("no translator available, raw dump: " + download_url(line))
-                return
+					continue
 			else:
 				if verbose:
 					phenny.say("error: HTTP " + str(response.status_code) + " " + download_url(line))
-                return
+					continue
 		else:
+			continue
 	return
 download.commands = ["fetch", "get", "download"]
 download.priority = "high"