Merge pull request #971 from open-contracting/957-anambra

nigeria: Add Bon Maximus base, update nigeria_anambra_state

docs/spiders.rst

@@ -923,12 +923,12 @@ Nigeria
 
    scrapy crawl nigeria_abia_state
 
-.. autoclass:: kingfisher_scrapy.spiders.nigeria_anambra_state_records.NigeriaAnambraStateRecords
+.. autoclass:: kingfisher_scrapy.spiders.nigeria_anambra_state.NigeriaAnambraState
    :no-members:
 
 .. code-block:: bash
 
-   scrapy crawl nigeria_anambra_state_records
+   scrapy crawl nigeria_anambra_state
 
 .. autoclass:: kingfisher_scrapy.spiders.nigeria_budeshi_records.NigeriaBudeshiRecords
    :no-members:

kingfisher_scrapy/spiders/nigeria_anambra_state.py

@@ -0,0 +1,17 @@
+from kingfisher_scrapy.spiders.nigeria_bon_maximus_base import NigeriaBonMaximusBase
+
+
+class NigeriaAnambraState(NigeriaBonMaximusBase):
+    """
+    Domain
+      Anambra State
+    API documentation
+      https://eprocure.bpp.an.gov.ng/awarded_contracts.php
+    """
+    name = 'nigeria_anambra_state'
+
+    # SimpleSpider
+    data_type = 'release_package'
+
+    # NigeriaBonMaximusBase
+    url_prefix = 'https://eprocure.bpp.an.gov.ng/'

kingfisher_scrapy/spiders/nigeria_bon_maximus_base.py

@@ -0,0 +1,23 @@
+import scrapy
+
+from kingfisher_scrapy.base_spiders import SimpleSpider
+from kingfisher_scrapy.util import components, get_parameter_value, handle_http_error
+
+
+class NigeriaBonMaximusBase(SimpleSpider):
+    # SimpleSpider
+    data_type = 'release_package'
+
+    # url_prefix must be provided by subclasses.
+
+    def start_requests(self):
+        url = f'{self.url_prefix}awarded_contracts.php'
+        yield scrapy.Request(url, meta={'file_name': 'all.html'}, callback=self.parse_list)
+
+    @handle_http_error
+    def parse_list(self, response):
+        for url in response.xpath('//table[@id="contractTable"]/tbody/tr/td[2]/a/@href').getall():
+            # The URLs look like
+            # https://url_prefix/existing_award_details.php?id=ocds-xwwr9a-000103-OS/HLT/02
+            ocid = get_parameter_value(url, 'id').replace('/', '_')
+            yield self.build_request(f'{self.url_prefix}media/{ocid}.json', formatter=components(-1))

kingfisher_scrapy/spiders/nigeria_osun_state.py

@@ -1,10 +1,7 @@
-import scrapy
+from kingfisher_scrapy.spiders.nigeria_bon_maximus_base import NigeriaBonMaximusBase
 
-from kingfisher_scrapy.base_spiders import SimpleSpider
-from kingfisher_scrapy.util import components, get_parameter_value, handle_http_error
 
-
-class NigeriaOsunState(SimpleSpider):
+class NigeriaOsunState(NigeriaBonMaximusBase):
     """
     Domain
       Nigeria Osun State Open Contracting Portal
@@ -16,17 +13,5 @@ class NigeriaOsunState(SimpleSpider):
     # SimpleSpider
     data_type = 'release_package'
 
-    # Local
+    # NigeriaBonMaximusBase
     url_prefix = 'https://egp.osunstate.gov.ng/'
-
-    def start_requests(self):
-        url = f'{self.url_prefix}awarded_contracts.php'
-        yield scrapy.Request(url, meta={'file_name': 'all.html'}, callback=self.parse_list)
-
-    @handle_http_error
-    def parse_list(self, response):
-        for url in response.xpath('//table[@id="contractTable"]/tbody/tr/td[2]/a/@href').getall():
-            # The URLs look like
-            # https://egp.osunstate.gov.ng/existing_award_details.php?id=ocds-xwwr9a-000103-OS/HLT/02
-            ocid = get_parameter_value(url, 'id').replace('/', '_')
-            yield self.build_request(f'{self.url_prefix}media/{ocid}.json', formatter=components(-1))