Add a config option to filter on terms in the description. Fix #77.

doc/0.getting_started.md

@@ -153,8 +153,12 @@ under the `constraints` key. The available constraints are:
   `null`) from the place identified by the GPS coordinates `LAT` and `LNG`
   (latitude and longitude), and we call this place `foobar` in human-readable
   form. Beware that `time` constraints are in **seconds**.
- * `minimum_nb_photos` let you filter out posts with less than this number of
+ * `minimum_nb_photos` lets you filter out posts with less than this number of
    photos.
+ * `description_should_contain` lets you specify a list of terms that should
+   be present in the posts descriptions. Typically, if you expect "parking" to
+   be in all the posts Flatisfy fetches for you, you can set
+   `description_should_contain: ["parking"]`.
 
 
 You can think of constraints as "a set of criterias to filter out flats". You

flatisfy/config.py

@@ -35,6 +35,7 @@ DEFAULT_CONFIG = {
             "rooms": (None, None),  # (min, max)
             "bedrooms": (None, None),  # (min, max)
             "minimum_nb_photos": None,  # min number of photos
+            "description_should_contain": [],  # list of terms
             "time_to": {}  # Dict mapping names to {"gps": [lat, lng],
                            #                        "time": (min, max) }
                            # Time is in seconds
@@ -144,6 +145,12 @@ def validate_config(config, check_with_data):
                 assert isinstance(constraint["minimum_nb_photos"], int)
                 assert constraint["minimum_nb_photos"] >= 0
 
+            assert "description_should_contain" in constraint
+            assert isinstance(constraint["description_should_contain"], list)
+            if constraint["description_should_contain"]:
+                for term in constraint["description_should_contain"]:
+                    assert isinstance(term, str)
+
             assert "house_types" in constraint
             assert constraint["house_types"]
             for house_type in constraint["house_types"]:

flatisfy/filters/__init__.py

@@ -80,12 +80,15 @@ def refine_with_housing_criteria(flats_list, constraint):
     )
 
 
-def refine_with_minimum_nb_photos(flats_list, constraint):
+def refine_with_details_criteria(flats_list, constraint):
     """
-    Filter a list of flats according to the minimum number of photos criterion.
+    Filter a list of flats according to the criteria which require the full
+    details to be fetched. These include minimum number of photos and terms
+    that should appear in description.
 
     .. note :: This has to be done in a separate function and not with the
-    other criterias as photos are only fetched in the second pass.
+    other criterias as photos and full description are only fetched in the
+    second pass.
 
     :param flats_list: A list of flats dict to filter.
     :param constraint: The constraint that the ``flats_list`` should satisfy.
@@ -111,6 +114,20 @@ def refine_with_minimum_nb_photos(flats_list, constraint):
             )
             is_ok[i] = False
 
+        has_terms_in_description = True
+        if constraint["description_should_contain"]:
+            has_terms_in_description = all(
+                term in flat['text']
+                for term in constraint["description_should_contain"]
+            )
+        if not has_terms_in_description:
+            LOGGER.info(
+                ("Description for flat %s does not contain all the required "
+                 "terms."),
+                flat["id"]
+            )
+            is_ok[i] = False
+
     return (
         [
             flat
@@ -202,9 +219,10 @@ def second_pass(flats_list, constraint, config):
     flats_list, ignored_list = refine_with_housing_criteria(flats_list,
                                                             constraint)
 
-    # Remove return housing posts which do not have enough photos
+    # Remove returned housing posts which do not match criteria relying on
-    flats_list, ignored_list = refine_with_minimum_nb_photos(flats_list,
+    # fetched details.
-                                                             constraint)
+    flats_list, ignored_list = refine_with_details_criteria(flats_list,
+                                                            constraint)
 
     return {
         "new": flats_list,