Add Teatro Castro Mendes spider

data_collector/data_collector/models.py

@@ -17,6 +17,7 @@ class Event(peewee.Model):
     location = peewee.CharField()
     published = peewee.BooleanField()
     image_path = peewee.CharField()
+    tags = peewee.TextField()
 
     class Meta:
         database = get_db()

data_collector/data_collector/pipelines.py

@@ -16,6 +16,7 @@ class DataCollectorPipeline:
     def process_item(self, item, spider):
         image_path = item["images"][0]["path"] if item["images"] else None
         location = re.sub(r"\s", " ", item["location"])
+        tags = item.get("tags") or []
 
         event = Event(
             title=item["title"],
@@ -26,6 +27,7 @@ class DataCollectorPipeline:
             location=location,
             published=False,
             image_path=image_path,
+            tags=",".join(tags),
         )
         try:
             event.save()

data_collector/data_collector/spiders/castro_mendes.py

@@ -0,0 +1,94 @@
+import copy
+import re
+from datetime import datetime, timedelta
+from urllib.parse import urlencode, urljoin
+
+import scrapy
+from slugify import slugify
+
+API_KEY = "live_2d2837a14f7043dab07f23022cb4fa3c1034caf1d92c4b198c86402146924c08"
+
+
+class CastroMendesSpider(scrapy.Spider):
+    name = "castro_mendes"
+    start_urls = [
+        f"https://api.teatrocastromendes.com.br/v1/home/card?apikey={API_KEY}"
+    ]
+
+    def parse(self, response):
+        for event in response.json():
+            event_url = urljoin("https://teatrocastromendes.com.br", event["uri"])
+            event_data = {
+                "title": event["ds_evento"],
+                "url": event_url,
+                "location": event["ds_nome_teatro"],
+                "image_urls": [
+                    event["img"],
+                ],
+                "tags": [
+                    "campinas",
+                    "castro-mendes",
+                    slugify(event["genreName"]),
+                ],
+            }
+
+            encoded_params = urlencode(
+                {
+                    "key": event["uri"].replace("/evento/", ""),
+                    "apikey": API_KEY,
+                }
+            )
+            event_details_url = "https://api.teatrocastromendes.com.br/v1/event/get"
+            url = f"{event_details_url}?{encoded_params}"
+
+            yield scrapy.Request(
+                url,
+                callback=self.parse_event,
+                cb_kwargs={"event_data": event_data},
+            )
+
+    def parse_event(self, response, event_data):
+        data = response.json()
+        event_data["description"] = data["description"]
+
+        encoded_params = urlencode(
+            {
+                "id_base": data["id_base"],
+                "codPeca": data["CodPeca"],
+                "apikey": API_KEY,
+            }
+        )
+        event_presentations_url = (
+            "https://api.teatrocastromendes.com.br/v1/event/presentation"
+        )
+        url = f"{event_presentations_url}?{encoded_params}"
+
+        yield scrapy.Request(
+            url,
+            callback=self.parse_presentations,
+            cb_kwargs={"event_data": event_data},
+        )
+
+    def parse_presentations(self, response, event_data):
+        for presentation in response.json():
+            presentation_data = copy.deepcopy(event_data)
+
+            hour = presentation["HorSessao"]
+            day = presentation["day"]
+            year = presentation["year"]
+
+            start_datetime = datetime.strptime(f"{day}/{year} {hour}", "%d/%m/%Y %H:%M")
+            presentation_data["start_datetime"] = start_datetime
+
+            duration = 60  # If not able to find event duration in description, use 60min as default
+            duration_match = re.findall(
+                r"Duração do espetáculo: (\d+) minutos", event_data["description"]
+            )
+            if duration_match:
+                duration = int(duration_match.pop())
+            end_datetime = datetime.strptime(
+                f"{day}/{year} {hour}", "%d/%m/%Y %H:%M"
+            ) + timedelta(minutes=duration)
+            presentation_data["end_datetime"] = start_datetime
+
+            yield presentation_data

poetry.lock

@@ -1445,6 +1445,23 @@ files = [
     {file = "PySocks-1.7.1.tar.gz", hash = "sha256:3f8804571ebe159c380ac6de37643bb4685970655d3bba243530d6558b799aa0"},
 ]
 
+[[package]]
+name = "python-slugify"
+version = "8.0.4"
+description = "A Python slugify application that also handles Unicode"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "python-slugify-8.0.4.tar.gz", hash = "sha256:59202371d1d05b54a9e7720c5e038f928f45daaffe41dd10822f3907b937c856"},
+    {file = "python_slugify-8.0.4-py2.py3-none-any.whl", hash = "sha256:276540b79961052b66b7d116620b36518847f52d5fd9e3a70164fc8c50faa6b8"},
+]
+
+[package.dependencies]
+text-unidecode = ">=1.3"
+
+[package.extras]
+unidecode = ["Unidecode (>=1.1.1)"]
+
 [[package]]
 name = "pyyaml"
 version = "6.0.2"
@@ -1691,6 +1708,17 @@ pure-eval = "*"
 [package.extras]
 tests = ["cython", "littleutils", "pygments", "pytest", "typeguard"]
 
+[[package]]
+name = "text-unidecode"
+version = "1.3"
+description = "The most basic Text::Unidecode port"
+optional = false
+python-versions = "*"
+files = [
+    {file = "text-unidecode-1.3.tar.gz", hash = "sha256:bad6603bb14d279193107714b288be206cac565dfa49aa5b105294dd5c4aab93"},
+    {file = "text_unidecode-1.3-py2.py3-none-any.whl", hash = "sha256:1311f10e8b895935241623731c2ba64f4c455287888b18189350b67134a822e8"},
+]
+
 [[package]]
 name = "tldextract"
 version = "5.1.3"
@@ -1889,4 +1917,4 @@ testing = ["coverage[toml]", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.13"
-content-hash = "4ea6ce1ed26377f323e9ce7c945ad7833485e6babeb505a6944833b830eb7375"
+content-hash = "22eb2ecfd0bdc6014c7ee3a73b62e2533b709251e442b4ae1053310afcd0cedd"

pyproject.toml

@@ -15,6 +15,7 @@ httpx = "^0.28.0"
 curlify2 = "^2.0.0"
 requests = "^2.32.3"
 pillow = "^11.0.0"
+python-slugify = "^8.0.4"
 
 
 [tool.poetry.group.dev.dependencies]