ingestr 0.13.36__tar.gz → 0.13.37__tar.gz

{ingestr-0.13.36 → ingestr-0.13.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.13.36
+Version: 0.13.37
 Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
 Project-URL: Homepage, https://github.com/bruin-data/ingestr
 Project-URL: Issues, https://github.com/bruin-data/ingestr/issues

{ingestr-0.13.36 → ingestr-0.13.37}/docs/.vitepress/config.mjs

@@ -119,6 +119,7 @@ export default defineConfig({
                 link: "/supported-sources/facebook-ads.md",
               },
               { text: "Frankfurter", link: "/supported-sources/frankfurter.md" },
+              { text: "Freshdesk", link: "/supported-sources/freshdesk.md" },
               { text: "Google Cloud Storage (GCS)", link: "/supported-sources/gcs.md" },
               { text: "Google Analytics", link: "/supported-sources/google_analytics.md" },
               { text: "Google Ads", link: "/supported-sources/google-ads.md" },

ingestr-0.13.37/ingestr/src/buildinfo.py

@@ -0,0 +1 @@
+version = "v0.13.37"

{ingestr-0.13.36 → ingestr-0.13.37}/ingestr/src/factory.py

@@ -54,6 +54,7 @@ from ingestr.src.sources import (
     TikTokSource,
     ZendeskSource,
     FreshdeskSource,
+    PhantombusterSource,
 )
 
 SQL_SOURCE_SCHEMES = [
@@ -150,6 +151,7 @@ class SourceDestinationFactory:
         "pipedrive": PipedriveSource,
         "frankfurter": FrankfurterSource,
         "freshdesk": FreshdeskSource,
+        "phantombuster": PhantombusterSource,
     }
     destinations: Dict[str, Type[DestinationProtocol]] = {
         "bigquery": BigQueryDestination,

ingestr-0.13.37/ingestr/src/phantombuster/__init__.py

@@ -0,0 +1,38 @@
+from typing import Iterable, Optional
+
+import dlt
+import pendulum
+import requests
+from dlt.common.typing import TDataItem
+from dlt.sources import DltResource
+from dlt.sources.helpers.requests import Client
+
+from ingestr.src.phantombuster.client import PhantombusterClient
+
+
+def retry_on_limit(
+    response: Optional[requests.Response], exception: Optional[BaseException]
+) -> bool:
+    if response is not None and response.status_code == 429:
+        return True
+    return False
+
+
+def create_client() -> requests.Session:
+    return Client(
+        raise_for_status=False,
+        retry_condition=retry_on_limit,
+        request_max_attempts=12,
+        request_backoff_factor=2,
+    ).session
+
+
+@dlt.source(max_table_nesting=0)
+def phantombuster_source(api_key: str, agent_id: str, start_date: pendulum.DateTime, end_date: pendulum.DateTime) -> Iterable[DltResource]:
+    client = PhantombusterClient(api_key)
+
+    @dlt.resource()
+    def completed_phantoms() -> Iterable[TDataItem]:
+        yield client.fetch_containers_result(create_client(), agent_id, start_date, end_date)
+
+    return completed_phantoms

ingestr-0.13.37/ingestr/src/phantombuster/client.py

@@ -0,0 +1,65 @@
+from typing import Union
+
+import pendulum
+import requests
+
+
+class PhantombusterClient:
+    def __init__(self, api_key: str):
+        self.api_key = api_key
+
+    def _get_headers(self):
+        return {
+            "X-Phantombuster-Key-1": self.api_key,
+            "accept": "application/json",
+        }
+
+    def fetch_containers_result(self, session: requests.Session, agent_id: str, start_date: pendulum.DateTime, end_date: pendulum.DateTime):
+        url = "https://api.phantombuster.com/api/v2/containers/fetch-all/"
+        before_ended_at = None
+        limit = 100
+        started_at = start_date.int_timestamp * 1000 + int(start_date.microsecond / 1000)
+        ended_at = end_date.int_timestamp * 1000 + int(end_date.microsecond / 1000)
+        while True:
+            params: dict[str, Union[str, int, float, bytes, None]] = {
+                "agentId": agent_id,
+                "limit": limit,
+                "mode": "finalized",
+            }
+
+            if before_ended_at:
+                params["beforeEndedAt"] = before_ended_at
+
+            response = session.get(url=url, headers=self._get_headers(), params=params)
+            data = response.json()
+            containers = data.get("containers", [])
+
+            for container in containers:
+                container_ended_at = container.get("endedAt")
+                if before_ended_at is None or before_ended_at > container["endedAt"]:
+                        before_ended_at = container["endedAt"]
+                        
+                if not (started_at <= container_ended_at <= ended_at):
+                    continue
+                try:
+                    result = self.fetch_result_object(session, container["id"])
+                    partition_dt = pendulum.from_timestamp(container_ended_at / 1000, tz="UTC").to_date_string()
+                    row = {"container": container, "result": result, "partition_dt": partition_dt}
+                    yield row
+                    
+                except requests.RequestException as e:
+                    print(f"Error fetching result for container {container['id']}: {e}")
+         
+            if data["maxLimitReached"] is False:
+                break
+ 
+
+    def fetch_result_object(self, session: requests.Session, container_id: str):
+        result_url = (
+            "https://api.phantombuster.com/api/v2/containers/fetch-result-object"
+        )
+        params = {"id": container_id}
+        response = session.get(result_url, headers=self._get_headers(), params=params)
+        response.raise_for_status()
+
+        return response.json()

{ingestr-0.13.36 → ingestr-0.13.37}/ingestr/src/sources.py

@@ -2231,4 +2231,44 @@ class FreshdeskSource:
         
         from ingestr.src.freshdesk import freshdesk_source
         return freshdesk_source(api_secret_key=api_key[0], domain=domain).with_resources(table)
-   
+
+class PhantombusterSource:
+    def handles_incrementality(self) -> bool:
+        return True
+    
+    def dlt_source(self, uri: str, table: str, **kwargs):
+        #phantombuster://?api_key=<api_key>
+        #source table = phantom_results:agent_id
+        parsed_uri = urlparse(uri)
+        params = parse_qs(parsed_uri.query)
+        api_key = params.get("api_key")
+        if api_key is None:
+            raise MissingValueError("api_key", "Phantombuster")
+        
+        table_fields = table.replace(" ", "").split(":")
+        table_name = table_fields[0]
+        
+        agent_id = table_fields[1] if len(table_fields) > 1 else None
+        
+        if table_name not in ["completed_phantoms"]:
+            raise UnsupportedResourceError(table_name, "Phantombuster")
+        
+        if not agent_id:
+            raise MissingValueError("agent_id", "Phantombuster")
+        
+        start_date = kwargs.get("interval_start")
+        if start_date is not None:
+            start_date = ensure_pendulum_datetime(start_date)
+        else:
+            start_date = pendulum.parse("2018-01-01")
+
+        end_date = kwargs.get("interval_end")
+        
+        #doesnot support incremental loading
+        if end_date is not None:
+            end_date = ensure_pendulum_datetime(end_date)
+        else:
+            end_date = pendulum.now()
+        
+        from ingestr.src.phantombuster import phantombuster_source
+        return phantombuster_source(api_key=api_key[0], agent_id=agent_id, start_date=start_date, end_date=end_date).with_resources(table_name)

ingestr-0.13.36/ingestr/src/buildinfo.py

@@ -1 +0,0 @@
-version = "v0.13.36"