Crawled and parsed and refacored and deleted and now blocked

bin/cache/cache_explore_page.py → bin/common/cache_explore_page.py

@@ -1,2 +1,2 @@
 from app.cached_items import cache_explore_context
-ctxt = cache_explore_context()
+ctxt = cache_explore_context()

bin/common/retry_decorator.py

@@ -0,0 +1,44 @@
+import time
+from functools import wraps
+
+def retry(ExceptionToCheck, tries=4, delay=3, backoff=2, logger=None):
+    """Retry calling the decorated function using an exponential backoff.
+
+    http://www.saltycrane.com/blog/2009/11/trying-out-retry-decorator-python/
+    original from: http://wiki.python.org/moin/PythonDecoratorLibrary#Retry
+
+    :param ExceptionToCheck: the exception to check. may be a tuple of
+        exceptions to check
+    :type ExceptionToCheck: Exception or tuple
+    :param tries: number of times to try (not retry) before giving up
+    :type tries: int
+    :param delay: initial delay between retries in seconds
+    :type delay: int
+    :param backoff: backoff multiplier e.g. value of 2 will double the delay
+        each retry
+    :type backoff: int
+    :param logger: logger to use. If None, print
+    :type logger: logging.Logger instance
+    """
+    def deco_retry(f):
+
+        @wraps(f)
+        def f_retry(*args, **kwargs):
+            mtries, mdelay = tries, delay
+            while mtries > 1:
+                try:
+                    return f(*args, **kwargs)
+                except ExceptionToCheck, e:
+                    msg = "%s, Retrying in %d seconds..." % (str(e), mdelay)
+                    if logger:
+                        logger.warning(msg)
+                    else:
+                        print msg
+                    time.sleep(mdelay)
+                    mtries -= 1
+                    mdelay *= backoff
+            return f(*args, **kwargs)
+
+        return f_retry  # true decorator
+
+    return deco_retry

bin/common/urllib.py

@@ -0,0 +1,7 @@
+
+import urllib2
+from retry_decorator import retry
+
+@retry(urllib2.URLError, tries=4, delay=3, backoff=2)
+def urlopen_with_retry(url):
+    return urllib2.urlopen(url)

bin/crawler/common

@@ -0,0 +1 @@
+../common/