🎉 New Source: The Guardian API [low-code CDK] (#18654)

* Add new source: The Guardian API

* Add documentation

* Fix custom paginator, it now stops without throwing an error

* Update the-guardian-api.md with PR number and link

* Remove catalog file, add titles to all properties in spec.yaml

* Add incremental sync, change parameter names

* format

* remove order from spec

* add guardian to source def

* auto-bump connector version

Co-authored-by: Vincent Koc <koconder@users.noreply.github.com>
Co-authored-by: marcosmarxm <marcosmarxm@gmail.com>
Co-authored-by: Octavia Squidington III <octavia-squidington-iii@users.noreply.github.com>
Co-authored-by: Marcos Marx <marcosmarxm@users.noreply.github.com>

airbyte-config/init/src/main/resources/seed/source_definitions.yaml

@@ -1334,6 +1334,13 @@
   icon: timely.svg
   sourceType: api
   releaseStage: alpha
+- name: The Guardian API
+  sourceDefinitionId: d42bd69f-6bf0-4d0b-9209-16231af07a92
+  dockerRepository: airbyte/source-the-guardian-api
+  dockerImageTag: 0.1.0
+  documentationUrl: https://docs.airbyte.com/integrations/sources/the-guardian-api
+  sourceType: api
+  releaseStage: alpha
 - name: Trello
   sourceDefinitionId: 8da67652-004c-11ec-9a03-0242ac130003
   dockerRepository: airbyte/source-trello

airbyte-config/init/src/main/resources/seed/source_specs.yaml

@@ -12858,6 +12858,78 @@
     supportsNormalization: false
     supportsDBT: false
     supported_destination_sync_modes: []
+- dockerImage: "airbyte/source-the-guardian-api:0.1.0"
+  spec:
+    documentationUrl: "https://docs.airbyte.com/integrations/sources/the-guardian-api"
+    connectionSpecification:
+      $schema: "http://json-schema.org/draft-07/schema#"
+      title: "The Guardian Api Spec"
+      type: "object"
+      required:
+      - "api_key"
+      - "start_date"
+      additionalProperties: true
+      properties:
+        api_key:
+          title: "API Key"
+          type: "string"
+          description: "Your API Key. See <a href=\"https://open-platform.theguardian.com/access/\"\
+            >here</a>. The key is case sensitive."
+          airbyte_secret: true
+        start_date:
+          title: "Start Date"
+          type: "string"
+          description: "Use this to set the minimum date (YYYY-MM-DD) of the results.\
+            \ Results older than the start_date will not be shown."
+          pattern: "^([1-9][0-9]{3})\\-(0?[1-9]|1[012])\\-(0?[1-9]|[12][0-9]|3[01])$"
+          examples:
+          - "YYYY-MM-DD"
+        query:
+          title: "Query"
+          type: "string"
+          description: "(Optional) The query (q) parameter filters the results to\
+            \ only those that include that search term. The q parameter supports AND,\
+            \ OR and NOT operators."
+          examples:
+          - "environment AND NOT water"
+          - "environment AND political"
+          - "amusement park"
+          - "political"
+        tag:
+          title: "Tag"
+          type: "string"
+          description: "(Optional) A tag is a piece of data that is used by The Guardian\
+            \ to categorise content. Use this parameter to filter results by showing\
+            \ only the ones matching the entered tag. See <a href=\"https://content.guardianapis.com/tags?api-key=test\"\
+            >here</a> for a list of all tags, and <a href=\"https://open-platform.theguardian.com/documentation/tag\"\
+            >here</a> for the tags endpoint documentation."
+          examples:
+          - "environment/recycling"
+          - "environment/plasticbags"
+          - "environment/energyefficiency"
+        section:
+          title: "Section"
+          type: "string"
+          description: "(Optional) Use this to filter the results by a particular\
+            \ section. See <a href=\"https://content.guardianapis.com/sections?api-key=test\"\
+            >here</a> for a list of all sections, and <a href=\"https://open-platform.theguardian.com/documentation/section\"\
+            >here</a> for the sections endpoint documentation."
+          examples:
+          - "media"
+          - "technology"
+          - "housing-network"
+        end_date:
+          title: "End Date"
+          type: "string"
+          description: "(Optional) Use this to set the maximum date (YYYY-MM-DD) of\
+            \ the results. Results newer than the end_date will not be shown. Default\
+            \ is set to the current date (today) for incremental syncs."
+          pattern: "^([1-9][0-9]{3})\\-(0?[1-9]|1[012])\\-(0?[1-9]|[12][0-9]|3[01])$"
+          examples:
+          - "YYYY-MM-DD"
+    supportsNormalization: false
+    supportsDBT: false
+    supported_destination_sync_modes: []
 - dockerImage: "airbyte/source-trello:0.1.6"
   spec:
     documentationUrl: "https://docs.airbyte.com/integrations/sources/trello"

airbyte-integrations/builds.md

@@ -121,6 +121,7 @@
 | Strava   | [![source-stava](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-strava%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-strava) |
 | Stripe   | [![source-stripe](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-stripe%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-stripe) |
 | Tempo   | [![source-tempo](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-tempo%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-tempo) |
+| The Guardian API | [![source-the-guardian-api](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-the-guardian-api%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-the-guardian-api) |
 | TikTok Marketing   | [![source-tiktok-marketing](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-tiktok-marketing%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-tiktok-marketing) |
 | Trello   | [![source-trello](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-trello%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-trello) |
 | Twilio   | [![source-twilio](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-twilio%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-twilio) |

airbyte-integrations/connectors/source-the-guardian-api/.dockerignore

@@ -0,0 +1,6 @@
+*
+!Dockerfile
+!main.py
+!source_the_guardian_api
+!setup.py
+!secrets

airbyte-integrations/connectors/source-the-guardian-api/Dockerfile

@@ -0,0 +1,38 @@
+FROM python:3.9.11-alpine3.15 as base
+
+# build and load all requirements
+FROM base as builder
+WORKDIR /airbyte/integration_code
+
+# upgrade pip to the latest version
+RUN apk --no-cache upgrade \
+    && pip install --upgrade pip \
+    && apk --no-cache add tzdata build-base
+
+
+COPY setup.py ./
+# install necessary packages to a temporary folder
+RUN pip install --prefix=/install .
+
+# build a clean environment
+FROM base
+WORKDIR /airbyte/integration_code
+
+# copy all loaded and built libraries to a pure basic image
+COPY --from=builder /install /usr/local
+# add default timezone settings
+COPY --from=builder /usr/share/zoneinfo/Etc/UTC /etc/localtime
+RUN echo "Etc/UTC" > /etc/timezone
+
+# bash is installed for more convenient debugging.
+RUN apk --no-cache add bash
+
+# copy payload code only
+COPY main.py ./
+COPY source_the_guardian_api ./source_the_guardian_api
+
+ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
+ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
+
+LABEL io.airbyte.version=0.1.0
+LABEL io.airbyte.name=airbyte/source-the-guardian-api

airbyte-integrations/connectors/source-the-guardian-api/README.md

@@ -0,0 +1,79 @@
+# The Guardian Api Source
+
+This is the repository for the The Guardian Api configuration based source connector.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/sources/the-guardian-api).
+
+## Local development
+
+#### Building via Gradle
+You can also build the connector in Gradle. This is typically used in CI and not needed for your development workflow.
+
+To build using Gradle, from the Airbyte repository root, run:
+```
+./gradlew :airbyte-integrations:connectors:source-the-guardian-api:build
+```
+
+#### Create credentials
+**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.io/integrations/sources/the-guardian-api)
+to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `source_the_guardian_api/spec.yaml` file.
+Note that any directory named `secrets` is gitignored across the entire Airbyte repo, so there is no danger of accidentally checking in sensitive information.
+See `integration_tests/sample_config.json` for a sample config file.
+
+**If you are an Airbyte core member**, copy the credentials in Lastpass under the secret name `source the-guardian-api test creds`
+and place them into `secrets/config.json`.
+
+### Locally running the connector docker image
+
+#### Build
+First, make sure you build the latest Docker image:
+```
+docker build . -t airbyte/source-the-guardian-api:dev
+```
+
+You can also build the connector image via Gradle:
+```
+./gradlew :airbyte-integrations:connectors:source-the-guardian-api:airbyteDocker
+```
+When building via Gradle, the docker image name and tag, respectively, are the values of the `io.airbyte.name` and `io.airbyte.version` `LABEL`s in
+the Dockerfile.
+
+#### Run
+Then run any of the connector commands as follows:
+```
+docker run --rm airbyte/source-the-guardian-api:dev spec
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/source-the-guardian-api:dev check --config /secrets/config.json
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/source-the-guardian-api:dev discover --config /secrets/config.json
+docker run --rm -v $(pwd)/secrets:/secrets -v $(pwd)/integration_tests:/integration_tests airbyte/source-the-guardian-api:dev read --config /secrets/config.json --catalog /integration_tests/configured_catalog.json
+```
+## Testing
+
+#### Acceptance Tests
+Customize `acceptance-test-config.yml` file to configure tests. See [Source Acceptance Tests](https://docs.airbyte.io/connector-development/testing-connectors/source-acceptance-tests-reference) for more information.
+If your connector requires to create or destroy resources for use during acceptance tests create fixtures for it and place them inside integration_tests/acceptance.py.
+
+To run your integration tests with docker
+
+### Using gradle to run tests
+All commands should be run from airbyte project root.
+To run unit tests:
+```
+./gradlew :airbyte-integrations:connectors:source-the-guardian-api:unitTest
+```
+To run acceptance and custom integration tests:
+```
+./gradlew :airbyte-integrations:connectors:source-the-guardian-api:integrationTest
+```
+
+## Dependency Management
+All of your dependencies should go in `setup.py`, NOT `requirements.txt`. The requirements file is only used to connect internal Airbyte dependencies in the monorepo for local development.
+We split dependencies between two groups, dependencies that are:
+* required for your connector to work need to go to `MAIN_REQUIREMENTS` list.
+* required for the testing need to go to `TEST_REQUIREMENTS` list
+
+### Publishing a new version of the connector
+You've checked out the repo, implemented a million dollar feature, and you're ready to share your changes with the world. Now what?
+1. Make sure your changes are passing unit and integration tests.
+1. Bump the connector version in `Dockerfile` -- just increment the value of the `LABEL io.airbyte.version` appropriately (we use [SemVer](https://semver.org/)).
+1. Create a Pull Request.
+1. Pat yourself on the back for being an awesome contributor.
+1. Someone from Airbyte will take a look at your PR and iterate with you to merge it into master.

airbyte-integrations/connectors/source-the-guardian-api/__init__.py

@@ -0,0 +1,3 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#

airbyte-integrations/connectors/source-the-guardian-api/acceptance-test-config.yml

@@ -0,0 +1,30 @@
+# See [Source Acceptance Tests](https://docs.airbyte.com/connector-development/testing-connectors/source-acceptance-tests-reference)
+# for more information about how to configure these tests
+connector_image: airbyte/source-the-guardian-api:dev
+acceptance_tests:
+  spec:
+    tests:
+      - spec_path: "source_the_guardian_api/spec.yaml"
+  connection:
+    tests:
+      - config_path: "secrets/config.json"
+        status: "succeed"
+      - config_path: "integration_tests/invalid_config.json"
+        status: "failed"
+  discovery:
+    tests:
+      - config_path: "secrets/config.json"
+  basic_read:
+    tests:
+      - config_path: "secrets/config.json"
+        configured_catalog_path: "integration_tests/configured_catalog.json"
+        empty_streams: []
+  incremental:
+    tests:
+      - config_path: "secrets/config.json"
+        configured_catalog_path: "integration_tests/configured_catalog.json"
+        future_state_path: "integration_tests/abnormal_state.json"
+  full_refresh:
+    tests:
+      - config_path: "secrets/config.json"
+        configured_catalog_path: "integration_tests/configured_catalog.json"

airbyte-integrations/connectors/source-the-guardian-api/acceptance-test-docker.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env sh
+
+# Build latest connector image
+docker build . -t $(cat acceptance-test-config.yml | grep "connector_image" | head -n 1 | cut -d: -f2-)
+
+# Pull latest acctest image
+docker pull airbyte/source-acceptance-test:latest
+
+# Run
+docker run --rm -it \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -v /tmp:/tmp \
+    -v $(pwd):/test_input \
+    airbyte/source-acceptance-test \
+    --acceptance-test-config /test_input
+

airbyte-integrations/connectors/source-the-guardian-api/bootstrap.md

@@ -0,0 +1,46 @@
+# The Guardian API
+
+## Overview
+
+[The Guardian Open Platform](https://open-platform.theguardian.com/) is a public web service for accessing all the content the Guardian creates, categorised by tags and section. To get started, You need a key to successfully authenticate against the API. The Guardian API Connector is implemented with the [Airbyte Low-Code CDK](https://docs.airbyte.com/connector-development/config-based/low-code-cdk-overview).
+
+## Output Format
+
+#### Each content item has the following structure:-
+
+```yaml
+{
+    "id": "string",
+    "type": "string"
+    "sectionId": "string"
+    "sectionName": "string"
+    "webPublicationDate": "string"
+    "webTitle": "string"
+    "webUrl": "string"
+    "apiUrl": "string"
+    "isHosted": "boolean"
+    "pillarId": "string"
+    "pillarName": "string"
+}
+```
+
+**Description:-**
+
+**webPublicationDate**: The combined date and time of publication
+**webUrl**: The URL of the html content
+**apiUrl**: The URL of the raw content
+
+## Core Streams
+
+Connector supports the `content` stream that returns all pieces of content in the API.
+
+## Rate Limiting
+
+The key that you are assigned is rate-limited and as such any applications that depend on making large numbers of requests on a polling basis are likely to exceed their daily quota and thus be prevented from making further requests until the next period begins.
+
+## Authentication and Permissions
+
+To access the API, you will need to sign up for an API key, which should be sent with every request. Visit [this](https://open-platform.theguardian.com/access) link to get an API key.
+The easiest way to see what data is included is to explore the data. You can build complex queries quickly and browse the results. Visit [this](https://open-platform.theguardian.com/explore) link to explore the data.
+
+See [this](https://docs.airbyte.io/integrations/sources/the-guardian-api) link for the connector docs.

airbyte-integrations/connectors/source-the-guardian-api/build.gradle

@@ -0,0 +1,9 @@
+plugins {
+    id 'airbyte-python'
+    id 'airbyte-docker'
+    id 'airbyte-source-acceptance-test'
+}
+
+airbytePython {
+    moduleDirectory 'source_the_guardian_api'
+}

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/__init__.py

@@ -0,0 +1,3 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/abnormal_state.json

@@ -0,0 +1,5 @@
+{
+  "content": {
+    "webPublicationDate": "2123-10-31T10:10:10Z"
+  }
+}

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/acceptance.py

@@ -0,0 +1,16 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+
+import pytest
+
+pytest_plugins = ("source_acceptance_test.plugin",)
+
+
+@pytest.fixture(scope="session", autouse=True)
+def connector_setup():
+    """This fixture is a placeholder for external resources that acceptance test might require."""
+    # TODO: setup test dependencies if needed. otherwise remove the TODO comments
+    yield
+    # TODO: clean up test dependencies

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/configured_catalog.json

@@ -0,0 +1,13 @@
+{
+  "streams": [
+    {
+      "stream": {
+        "name": "content",
+        "json_schema": {},
+        "supported_sync_modes": ["full_refresh", "incremental"]
+      },
+      "sync_mode": "incremental",
+      "destination_sync_mode": "overwrite"
+    }
+  ]
+}

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/invalid_config.json

@@ -0,0 +1,5 @@
+{
+  "api_key": "<invalid api_key>",
+  "query": "water OR rain",
+  "start_date": "2022-10-25"
+}

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/sample_config.json

@@ -0,0 +1,5 @@
+{
+  "api_key": "<valid api_key>",
+  "query": "water OR rain OR thunder",
+  "start_date": "2022-10-25"
+}

airbyte-integrations/connectors/source-the-guardian-api/integration_tests/sample_state.json

@@ -0,0 +1,5 @@
+{
+  "content": {
+    "webPublicationDate": "2022-10-25T10:10:10Z"
+  }
+}