tsr/planet
1
0
Fork 0
Code Issues 3 Pull Requests Releases Wiki Activity

First attempt at blacklisting

Browse Source
This commit is contained in:
Mikael Nilsson 2010-06-01 16:55:51 +02:00
parent 5c7edd7f56
commit 552dae3c14
2 changed files with 18 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
planet/config.py
View File

@ -303,7 +303,7 @@ def downloadReadingList(list, orig_config, callback, use_cache=True, re_read=Tru
def http_cache_directory():
if parser.has_option('Planet', 'http_cache_directory'):
os.path.join(cache_directory(),
return os.path.join(cache_directory(),
parser.get('Planet', 'http_cache_directory'))
else:
return os.path.join(cache_directory(), "cache")
@ -315,9 +315,16 @@ def cache_sources_directory():
else:
return os.path.join(cache_directory(), 'sources')
def cache_blacklist_directory():
if parser.has_option('Planet', 'cache_blacklist_directory'):
return os.path.join(cache_directory(),
parser.get('Planet', 'cache_blacklist_directory'))
else:
return os.path.join(cache_directory(), 'blacklist')
def cache_lists_directory():
if parser.has_option('Planet', 'cache_lists_directory'):
parser.get('Planet', 'cache_lists_directory')
return parser.get('Planet', 'cache_lists_directory')
else:
return os.path.join(cache_directory(), 'lists')
@ -332,7 +339,7 @@ def feed():
def feedtype():
if parser.has_option('Planet', 'feedtype'):
parser.get('Planet', 'feedtype')
return parser.get('Planet', 'feedtype')
elif feed() and feed().find('atom')>=0:
return 'atom'
elif feed() and feed().find('rss')>=0:

8
planet/spider.py
View File

@ -69,6 +69,7 @@ def _is_http_uri(uri):
def writeCache(feed_uri, feed_info, data):
log = planet.logger
sources = config.cache_sources_directory()
blacklist = config.cache_blacklist_directory()
# capture http status
if not data.has_key("status"):
@ -190,6 +191,13 @@ def writeCache(feed_uri, feed_info, data):
cache = config.cache_directory()
for updated, entry in ids.values():
# compute blacklist file name based on the id
blacklist_file = filename(blacklist, entry.id)
# check if blacklist file exists. If so, skip it.
if os.path.exists(blacklist_file):
continue
# compute cache file name based on the id
cache_file = filename(cache, entry.id)