Do not store personal data by default, let user overload this behavior

through config.

Fixes #80.

doc/0.getting_started.md

@@ -113,6 +113,10 @@ List of configuration options:
   doc](http://bottlepy.org/docs/dev/deployment.html).
 * `backends` is a list of Weboob backends to enable. It defaults to any
   available and supported Weboob backend.
+* `store_personal_data` is a boolean indicated whether or not Flatisfy should
+  fetch personal data from housing posts and store them in database. Such
+  personal data include contact phone number for instance. By default,
+  Flatisfy does not store such personal data.
 
 _Note:_ In production, you can either use the `serve` command with a reliable
 webserver instead of the default Bottle webserver (specifying a `webserver`

flatisfy/config.py

@@ -41,6 +41,9 @@ DEFAULT_CONFIG = {
                            # Time is in seconds
         }
     },
+    # Whether or not to store personal data from housing posts (phone number
+    # etc)
+    "store_personal_data": False,
     # Navitia API key
     "navitia_api_key": None,
     # Number of filtering passes to run
@@ -133,6 +136,8 @@ def validate_config(config, check_with_data):
         assert config["smtp_port"] is None or isinstance(config["smtp_port"], int)  # noqa: E501
         assert config["smtp_to"] is None or isinstance(config["smtp_to"], list)
 
+        assert isinstance(config["store_personal_data"], bool)
+
         # Ensure constraints are ok
         assert config["constraints"]
         for constraint in config["constraints"].values():

flatisfy/fetch.py

@@ -173,12 +173,14 @@ class WeboobProxy(object):
 
         return queries
 
-    def query(self, query, max_entries=None):
+    def query(self, query, max_entries=None, store_personal_data=False):
         """
         Fetch the housings posts matching a given Weboob query.
 
         :param query: A Weboob `weboob.capabilities.housing.Query`` object.
         :param max_entries: Maximum number of entries to fetch.
+        :param store_personal_data: Whether personal data should be fetched
+        from housing posts (phone number etc).
         :return: The matching housing posts, dumped as a list of JSON objects.
         """
         housings = []
@@ -188,6 +190,8 @@ class WeboobProxy(object):
                     self.webnip.do('search_housings', query),
                     max_entries
             ):
+                if not store_personal_data:
+                    housing.phone = None
                 housings.append(json.dumps(housing, cls=WeboobEncoder))
         except CallErrors as exc:
             # If an error occured, just log it
@@ -197,12 +201,14 @@ class WeboobProxy(object):
             )
         return housings
 
-    def info(self, full_flat_id):
+    def info(self, full_flat_id, store_personal_data=False):
         """
         Get information (details) about an housing post.
 
         :param full_flat_id: A Weboob housing post id, in complete form
         (ID@BACKEND)
+        :param store_personal_data: Whether personal data should be fetched
+        from housing posts (phone number etc).
         :return: The details in JSON.
         """
         flat_id, backend_name = full_flat_id.rsplit("@", 1)
@@ -220,6 +226,9 @@ class WeboobProxy(object):
             housing = backend.get_housing(flat_id)
             # Otherwise, we miss the @backend afterwards
             housing.id = full_flat_id
+            # Eventually clear personal data
+            if not store_personal_data:
+                housing.phone = None
 
             return json.dumps(housing, cls=WeboobEncoder)
         except Exception as exc:  # pylint: disable=broad-except
@@ -249,7 +258,8 @@ def fetch_flats(config):
             housing_posts = []
             for query in queries:
                 housing_posts.extend(
-                    weboob_proxy.query(query, config["max_entries"])
+                    weboob_proxy.query(query, config["max_entries"],
+                                       config["store_personal_data"])
                 )
         LOGGER.info("Fetched %d flats.", len(housing_posts))
 
@@ -270,7 +280,8 @@ def fetch_details(config, flat_id):
     """
     with WeboobProxy(config) as weboob_proxy:
         LOGGER.info("Loading additional details for flat %s.", flat_id)
-        weboob_output = weboob_proxy.info(flat_id)
+        weboob_output = weboob_proxy.info(flat_id,
+                                          config["store_personal_data"])
 
     flat_details = json.loads(weboob_output)
     flat_details = WeboobProxy.restore_decimal_fields(flat_details)