Improve client to use it via IDE

README.rst

@@ -88,7 +88,7 @@ Jobs instance is described well in ``Jobs`` section below.
 
 For example, to schedule a spider run (it returns a job object)::
 
-    >>> project.jobs.schedule('spider1', spider_args={'arg1':'val1'})
+    >>> project.jobs.schedule('spider1', job_args={'arg1':'val1'})
     <scrapinghub.client.Job at 0x106ee12e8>>
 
 Project instance also has the following fields:
@@ -151,7 +151,7 @@ Like project instance, spider instance has ``jobs`` field to work with the spide
 
 To schedule a spider run::
 
-    >>> spider.jobs.schedule(spider_args={'arg1:'val1'})
+    >>> spider.jobs.schedule(job_args={'arg1:'val1'})
     <scrapinghub.client.Job at 0x106ee12e8>>
 
 Note that you don't need to specify spider name explicitly.

scrapinghub/client/__init__.py

@@ -51,44 +51,43 @@ def __init__(self, auth=None, dash_endpoint=None, **kwargs):
                                       url=dash_endpoint)
         self._hsclient = HubstorageClient(auth=(login, password), **kwargs)
 
-    def get_project(self, projectid):
+    def get_project(self, project_id):
         """Get :class:`Project` instance with a given project id.
 
         The method is a shortcut for client.projects.get().
 
-        :param projectid: integer or string numeric project id.
+        :param project_id: integer or string numeric project id.
         :return: :class:`Project` object.
-        :rtype: scrapinghub.client.Project.
+        :rtype: scrapinghub.client.projects.Project
 
         Usage::
 
             >>> project = client.get_project(123)
             >>> project
-            <scrapinghub.client.Project at 0x106cdd6a0>
+            <scrapinghub.client.projects.Project at 0x106cdd6a0>
         """
-        return self.projects.get(parse_project_id(projectid))
+        return self.projects.get(parse_project_id(project_id))
 
-    def get_job(self, jobkey):
-        """Get Job with a given jobkey.
+    def get_job(self, job_key):
+        """Get Job with a given job key.
 
-        :param jobkey: job key string in format 'project/spider/job',
+        :param job_key: job key string in format 'project_id/spider_id/job_id',
             where all the components are integers.
         :return: :class:`Job` object.
-        :rtype: scrapinghub.client.Job.
+        :rtype: scrapinghub.client.jobs.Job
 
         Usage::
 
             >>> job = client.get_job('123/1/1')
             >>> job
-            <scrapinghub.client.Job at 0x10afe2eb1>
+            <scrapinghub.client.jobs.Job at 0x10afe2eb1>
         """
-        projectid = parse_job_key(jobkey).projectid
-        return self.projects.get(projectid).jobs.get(jobkey)
+        project_id = parse_job_key(job_key).project_id
+        return self.projects.get(project_id).jobs.get(job_key)
 
     def close(self, timeout=None):
         """Close client instance.
 
-        :param timeout: (optional) float timeout secs to stop everything
-            gracefully.
+        :param timeout: (optional) float timeout secs to stop gracefully.
         """
         self._hsclient.close(timeout=timeout)

scrapinghub/client/activity.py

@@ -49,12 +49,17 @@ def __init__(self, *args, **kwargs):
         self._wrap_iter_methods(['iter'])
 
     def add(self, values, **kwargs):
+        """Add new event to the project activity.
+
+        :param values: a single event or a list of events, where event is
+            represented with a dictionary of ('event', 'job', 'user') keys.
+        """
         if not isinstance(values, list):
             values = list(values)
         for activity in values:
             if not isinstance(activity, dict):
                 raise ValueError("Please pass events as dictionaries")
-            jobkey = activity.get('job')
-            if jobkey and parse_job_key(jobkey).projectid != self.key:
+            job_key = activity.get('job')
+            if job_key and parse_job_key(job_key).project_id != self.key:
                 raise ValueError('Please use same project id')
         self._origin.post(values, **kwargs)

scrapinghub/client/collections.py

@@ -5,10 +5,9 @@
 
 from ..hubstorage.collectionsrt import Collection as _Collection
 
-from .utils import _Proxy
-from .utils import format_iter_filters
-from .utils import proxy_methods
-from .utils import wrap_kwargs
+from .utils import (
+    _Proxy, format_iter_filters, proxy_methods, wrap_kwargs, update_kwargs,
+)
 
 
 class Collections(_Proxy):
@@ -25,29 +24,75 @@ class Collections(_Proxy):
         >>> foo_store = collections.get_store('foo_store')
     """
 
-    def get(self, coltype, colname):
-        """Base method to get a collection with a given type and name."""
-        self._origin._validate_collection(coltype, colname)
-        return Collection(self._client, self, coltype, colname)
+    def get(self, type_, name):
+        """Base method to get a collection with a given type and name.
 
-    def get_store(self, colname):
-        return self.get('s', colname)
+        :param type_: a collection type string.
+        :param name: a collection name string.
+        :return: :class:`Collection` object.
+        :rtype: Collection
+        """
+        self._origin._validate_collection(type_, name)
+        return Collection(self._client, self, type_, name)
+
+    def get_store(self, name):
+        """Method to get a store collection by name.
+
+        :param name: a collection name string.
+        :return: :class:`Collection` object.
+        :rtype: Collection
+        """
+        return self.get('s', name)
+
+    def get_cached_store(self, name):
+        """Method to get a cashed-store collection by name.
+
+        The collection type means that items expire after a month.
+
+        :param name: a collection name string.
+        :return: :class:`Collection` object.
+        :rtype: Collection
+        """
+        return self.get('cs', name)
+
+    def get_versioned_store(self, name):
+        """Method to get a versioned-store collection by name.
+
+        The collection type retains up to 3 copies of each item.
+
+        :param name: a collection name string.
+        :return: :class:`Collection` object.
+        :rtype: Collection
+        """
+        return self.get('vs', name)
 
-    def get_cached_store(self, colname):
-        return self.get('cs', colname)
+    def get_versioned_cached_store(self, name):
+        """Method to get a versioned-cached-store collection by name.
 
-    def get_versioned_store(self, colname):
-        return self.get('vs', colname)
+        Multiple copies are retained, and each one expires after a month.
 
-    def get_versioned_cached_store(self, colname):
-        return self.get('vcs', colname)
+        :param name: a collection name string.
+        :return: :class:`Collection` object.
+        :rtype: Collection
+        """
+        return self.get('vcs', name)
 
     def iter(self):
-        """Iterate through collections of a project."""
+        """Iterate through collections of a project.
+
+        :return: an iterator over collections list where each collection is
+            represented by a dictionary with ('name','type') fields.
+        :rtype: collections.Iterable[dict]
+        """
         return self._origin.apiget('list')
 
     def list(self):
-        """List collections of a project."""
+        """List collections of a project.
+
+        :return: a list of collections where each collection is
+            represented by a dictionary with ('name','type') fields.
+        :rtype: list[dict]
+        """
         return list(self.iter())
 
 
@@ -56,7 +101,7 @@ class Collection(object):
 
     Not a public constructor: use :class:`Collections` instance to get a
     :class:`Collection` instance. See :meth:`Collections.get_store` and
-    similar methods.  # noqa
+    similar methods.
 
     Usage:
 
@@ -84,8 +129,7 @@ class Collection(object):
 
         >>> for elem in foo_store.iter(count=1)):
         >>> ... print(elem)
-        [{'_key': '002d050ee3ff6192dcbecc4e4b4457d7',
-            'value': '1447221694537'}]
+        [{'_key': '002d050ee3ff6192dcbecc4e4b4457d7', 'value': '1447221694537'}]
 
     - filter by multiple keys, only values for keys that exist will be returned::
 
@@ -97,9 +141,9 @@ class Collection(object):
         >>> foo_store.delete('002d050ee3ff6192dcbecc4e4b4457d7')
     """
 
-    def __init__(self, client, collections, coltype, colname):
+    def __init__(self, client, collections, type_, name):
         self._client = client
-        self._origin = _Collection(coltype, colname, collections._origin)
+        self._origin = _Collection(type_, name, collections._origin)
         proxy_methods(self._origin, self, [
             'create_writer', 'count',
             ('iter', 'iter_values'),
@@ -111,35 +155,58 @@ def __init__(self, client, collections, coltype, colname):
             wrapped = wrap_kwargs(getattr(self, method), format_iter_filters)
             setattr(self, method, wrapped)
 
-    def list(self, *args, **kwargs):
+    def list(self, key=None, prefix=None, prefixcount=None, startts=None,
+             endts=None, requests_params=None, **params):
         """Convenient shortcut to list iter results.
 
         Please note that list() method can use a lot of memory and for a large
         amount of elements it's recommended to iterate through it via iter()
         method (all params and available filters are same for both methods).
+
+        :param key: a string key or a list of keys to filter with.
+        :param prefix: a string prefix to filter items.
+        :param prefixcount: maximum number of values to return per prefix.
+        :param startts: UNIX timestamp at which to begin results.
+        :param endts: UNIX timestamp at which to end results.
+        :param requests_params: (optional) a dict with optional requests params.
+        :param \*\*params: (optional) additional query params for the request.
+        :return: a list of items where each item is represented with a dict.
+        :rtype: list[dict]
+
+        # FIXME there should be similar docstrings for iter/iter_raw_json
+        # but as we proxy them as-is, it's not in place, should be improved
         """
-        return list(self.iter(*args, **kwargs))
+        update_kwargs(params, key=key, prefix=prefix, prefixcount=prefixcount,
+                      startts=startts, endts=endts,
+                      requests_params=requests_params)
+        return list(self.iter(requests_params=None, **params))
 
-    def get(self, key, *args, **kwargs):
+    def get(self, key, **params):
         """Get item from collection by key.
 
-        :param key: string item key
-        :return: an item dictionary if exists
+        :param key: string item key.
+        :param \*\*params: (optional) additional query params for the request.
+        :return: an item dictionary if exists.
+        :rtype: dict
         """
         if key is None:
             raise ValueError("key cannot be None")
-        return self._origin.get(key, *args, **kwargs)
+        return self._origin.get(key, **params)
 
-    def set(self, *args, **kwargs):
+    def set(self, value):
         """Set item to collection by key.
 
+        :param value: a dict representing a collection item.
+
         The method returns None (original method returns an empty generator).
         """
-        self._origin.set(*args, **kwargs)
+        self._origin.set(value)
 
     def delete(self, keys):
         """Delete item(s) from collection by key(s).
 
+        :param keys: a single key or a list of keys.
+
         The method returns None (original method returns an empty generator).
         """
         if (not isinstance(keys, string_types) and
@@ -148,7 +215,24 @@ def delete(self, keys):
                              "object providing string keys")
         self._origin.delete(keys)
 
-    def iter_raw_msgpack(self, requests_params=None, **apiparams):
+    def iter_raw_msgpack(self, key=None, prefix=None, prefixcount=None,
+                         startts=None, endts=None, requests_params=None,
+                         **params):
+        """A method to iterate through raw msgpack-ed items.
+        Can be convenient if data is needed in same msgpack format.
+
+        :param key: a string key or a list of keys to filter with.
+        :param prefix: a string prefix to filter items.
+        :param prefixcount: maximum number of values to return per prefix.
+        :param startts: UNIX timestamp at which to begin results.
+        :param endts: UNIX timestamp at which to end results.
+        :param requests_params: (optional) a dict with optional requests params.
+        :param \*\*params: (optional) additional query params for the request.
+        :return: an iterator over items list packed with msgpack.
+        :rtype: collections.Iterable[bytes]
+        """
+        update_kwargs(params, key=key, prefix=prefix, prefixcount=prefixcount,
+                      startts=startts, endts=endts,
+                      requests_params=requests_params)
         return self._origin._collections.iter_msgpack(
-            self._origin.coltype, self._origin.colname,
-            requests_params=requests_params, **apiparams)
+            self._origin.coltype, self._origin.colname, **params)