tweak

.gitignore

@@ -9,7 +9,7 @@ Desktop.ini
 *.pyc
 
 # Private settings file
-bigcases_settings.py
+
 
 # Recycle Bin used on file shares
 $RECYCLE.BIN/

bigcases_scrape_docs.py

@@ -104,7 +104,7 @@ def getDocument(pid, url):
 
 		# Now fish out the most recent file and stick it where you want it
 
-		files = glob.glob(settings.file_temp_path + '*')
+		files = glob.glob(settings.file_temp_path + '/*')
 		files.sort(key=os.path.getmtime, reverse=True)
 		if len(files) >= 2:
 			newfn = settings.file_archive_path + '/document-' + str(pid) + '.pdf'

bigcases_settings.py

@@ -0,0 +1,34 @@
+
+class settings:
+
+	# Scrape settings
+	multitask = False					# Use multiprocessing for scraping RSS?
+	multitask_threads = 5
+	http_timeout = 30.0					# How long to wait for http requests
+	file_temp_path = ''					# Set a temporary path for working with PDFs (i.e., /data/pacer)
+	file_archive_path = ''				# Set a folder to archive downloaded PDFs (i.e., /data/pacer/archive)
+	max_files_to_scrape = 10
+
+	# Database settings (MySQL server)
+	db_host = ''						# MySQL host name
+	db_user = ''						# MySQL username
+	db_pass = ''						# MySQL password
+	db_port = 3306						# MySQL port
+
+	# PACER settings
+	pacer_user = ''					# PACER username
+	pacer_pass = ''					# PACER password
+	pacer_client = ''					# PACER client code
+	pacer_max_price = 3.00				# Maximum amount to pay for PACER record
+
+	# DocumentCloud credentials
+	dc_user = ''						# DocumentCloud username
+	dc_pass = ''						# DocumentCloud password
+	dc_project_id = ''					# Numeric ID of DocumentCloud project to which to post
+
+	# Twitter credentials
+	twitter_app_key = ''
+	twitter_app_secret = ''
+	twitter_oauth_key = ''
+	twitter_oauth_secret = ''
+