Initial commit - Data scraper for Jundiaí events

.gitignore

@@ -0,0 +1,182 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+# Generated using ignr.py - github.com/Antrikshy/ignr.py
+
+.~lock*
+*.swp
+*.csv

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+-   repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+    -   id: isort
+        name: isort (python)
+-   repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.10.0
+    hooks:
+    -   id: black
+        language_version: python3.11

.python-version

@@ -0,0 +1 @@
+3.13.0

data_collector/data_collector/items.py

@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DataCollectorItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

data_collector/data_collector/middlewares.py

@@ -0,0 +1,102 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter, is_item
+from scrapy import signals
+
+
+class DataCollectorSpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, or item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request or item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class DataCollectorDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)

data_collector/data_collector/models.py

@@ -0,0 +1,31 @@
+import peewee
+
+from data_collector import settings
+
+
+def get_db():
+    return peewee.SqliteDatabase(settings.DATABASE)
+
+
+class Event(peewee.Model):
+    title = peewee.CharField()
+    start_datetime = peewee.DateTimeField()
+    end_datetime = peewee.DateTimeField()
+    url = peewee.CharField()
+    location = peewee.CharField()
+    processed = peewee.BooleanField()
+
+    class Meta:
+        database = get_db()
+        indexes = ((("title", "start_datetime", "end_datetime", "url"), True),)
+
+
+def initialize_db():
+    db = get_db()
+    db.connect(reuse_if_open=True)
+    db.create_tables(
+        [
+            Event,
+        ]
+    )
+    return db

data_collector/data_collector/pipelines.py

@@ -0,0 +1,30 @@
+import peewee
+from itemadapter import ItemAdapter
+
+from data_collector.models import Event, initialize_db
+
+
+class DataCollectorPipeline:
+
+    def open_spider(self, spider):
+        self.db = initialize_db()
+
+    def process_item(self, item, spider):
+        event = Event(
+            title=item["title"],
+            start_datetime=item["start_datetime"],
+            end_datetime=item["end_datetime"],
+            url=item["url"],
+            location=item["location"],
+            processed=False,
+        )
+        try:
+            event.save()
+        except peewee.IntegrityError:
+            # Event was added before
+            pass
+
+        return item
+
+    def close_spider(self, spider):
+        self.db.close()

data_collector/data_collector/settings.py

@@ -0,0 +1,94 @@
+# Scrapy settings for data_collector project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = "data_collector"
+
+SPIDER_MODULES = ["data_collector.spiders"]
+NEWSPIDER_MODULE = "data_collector.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+# USER_AGENT = "data_collector (+http://www.yourdomain.com)"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+# CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+# DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+# CONCURRENT_REQUESTS_PER_DOMAIN = 16
+# CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+# COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+# TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+# DEFAULT_REQUEST_HEADERS = {
+#    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+#    "Accept-Language": "en",
+# }
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    "data_collector.middlewares.DataCollectorSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "data_collector.middlewares.DataCollectorDownloaderMiddleware": 543,
+# }
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+# EXTENSIONS = {
+#    "scrapy.extensions.telnet.TelnetConsole": None,
+# }
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    "data_collector.pipelines.DataCollectorPipeline": 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+# AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+# AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+# AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+# AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+# HTTPCACHE_ENABLED = True
+# HTTPCACHE_EXPIRATION_SECS = 0
+# HTTPCACHE_DIR = "httpcache"
+# HTTPCACHE_IGNORE_HTTP_CODES = []
+# HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"
+
+# Set settings whose default value is deprecated to a future-proof value
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"
+
+DATABASE = "agenda.db"

data_collector/data_collector/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

data_collector/data_collector/spiders/cultura_jundiai.py

@@ -0,0 +1,36 @@
+import re
+from datetime import datetime
+
+import scrapy
+
+
+class CulturaJundiaiSpider(scrapy.Spider):
+    name = "cultura_jundiai"
+    allowed_domains = ["cultura.jundiai.sp.gov.br"]
+    start_urls = ["https://cultura.jundiai.sp.gov.br/agenda-cultural/"]
+    date_regex = r"(?P<date>\d{2}\/\d{2}\/\d{4}).*(?P<start_time>\d{2}:\d{2}).*(?P<end_time>\d{2}:\d{2})"
+
+    def parse(self, response):
+        for event in response.css(".noticia-lista"):
+            event_date = event.css(".data-lista p::text").get()
+
+            date_search = re.search(self.date_regex, event_date)
+            if date_search:
+                date = date_search.groupdict()["date"]
+                start_time = date_search.groupdict()["start_time"]
+                start_datetime = datetime.strptime(
+                    f"{date} {start_time}", "%d/%m/%Y %H:%M"
+                )
+                end_time = date_search.groupdict()["end_time"]
+                end_datetime = datetime.strptime(f"{date} {end_time}", "%d/%m/%Y %H:%M")
+
+                yield {
+                    "title": event.css(".titulo-lista::text").get(),
+                    "start_datetime": start_datetime,
+                    "end_datetime": end_datetime,
+                    "url": event.css("a::attr(href)").get(),
+                    "location": event.css(".resumo-lista::text").get(),
+                }
+
+        for page_url in response.css("#paginacao a::attr(href)").getall():
+            yield scrapy.Request(page_url)

data_collector/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = data_collector.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = data_collector

pyproject.toml

@@ -0,0 +1,29 @@
+[tool.poetry]
+name = "agenda"
+version = "0.1.0"
+description = ""
+authors = ["Renne Rocha <renne@rocha.dev.br>"]
+license = "GNU GPLv3"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.13"
+scrapy = "^2.12.0"
+peewee = "^3.17.8"
+
+
+[tool.poetry.group.dev.dependencies]
+ipython = "^8.30.0"
+ipdb = "^0.13.13"
+black = "^24.10.0"
+pre-commit = "^4.0.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.isort]
+known_first_party = ["data_collector"]
+known_third_party = ["scrapy"]
+profile = "black"
+sections = ["FUTURE", "STDLIB", "THIRDPARTY", "FIRSTPARTY", "LOCALFOLDER"]