Desafio-Webcrawler Matheus Ferreira

.gitignore

@@ -0,0 +1,129 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/

README.md

@@ -1,5 +1,38 @@
 # Desafio Webcrawler BIT
 
+
+# Considerações 🚀
+
+## Rodando o projeto
+
+1 - Rodar o comando abaixo para instalar as dependências:
+
+```pip install -r requirements.txt```
+
+2 - Instalar o MongoDB
+
+https://www.mongodb.com/try/download/community
+
+3 - Feita a instalação, iniciar o MongoDB (arquivo mongod.exe, ou adicionar ao PATH)
+
+4 - Para rodar o scrapy, no diretório do arquivo rodar o comando:
+
+```python
+scrapy crawl quotes
+```
+
+## Rodando as queries
+
+1 - Para rodar as queries, rodar o comando abaixo para instalar as dependências do MongoDB no Node.JS:
+
+```npm install mongodb```
+
+2 - Por fim, no diretório queries_js, rodar o comando:
+
+```python
+node <filename>
+```
+
 ## Sobre
 
 O desafio consiste na implementação de um _crawler_ que colete e armazene citações do site _http://quotes.toscrape.com_.

desafiowebcrawler/desafiowebcrawler/items.py

@@ -0,0 +1,14 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DesafiowebcrawlerItem(scrapy.Item):
+    # define the fields for your item here like:
+    title = scrapy.Field()
+    author = scrapy.Field()
+    tag = scrapy.Field()
+    pass

desafiowebcrawler/desafiowebcrawler/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class DesafiowebcrawlerSpiderMiddleware:
+    # 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 DesafiowebcrawlerDownloaderMiddleware:
+    # 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)

desafiowebcrawler/desafiowebcrawler/pipelines.py

@@ -0,0 +1,29 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+import pymongo
+
+class DesafiowebcrawlerPipeline(object):
+
+    def __init__(self):
+        ## Conectando no mongodb
+        self.conn = pymongo.MongoClient(
+            'localhost',
+            27017
+        )
+
+        ## Criando o banco
+        db = self.conn['quotestoscrape']
+        ## Criando a tabela
+        self.collection = db['matheus_ferreira']
+        #### Dropei a collection para nao duplicar os dados caso rode o scrapy duas vezes na mesma pagina
+        self.collection.drop()
+
+    def process_item(self, item, spider):
+        self.collection.insert_one(dict(item))
+        return item

desafiowebcrawler/desafiowebcrawler/queries_js/count_distinct_authors_titles.js

@@ -0,0 +1,31 @@
+//Query para retornar o numero de titulos recuperados por autor
+// Ordenados por quantidade, seguido de nome
+var MongoClient = require('mongodb').MongoClient;
+var url = "mongodb://localhost:27017/";
+
+MongoClient.connect(url, function(err, db) {
+    if (err) throw err;
+    var dbo = db.db("quotestoscrape");
+    dbo.collection('matheus_ferreira').aggregate([
+    {
+        "$unwind": "$author.name"
+    },
+    {
+        "$group": {
+            "_id": "$author.name",
+            "qtd": {
+                "$sum": 1
+            }
+        }
+      },
+    {
+        "$sort": {qtd: -1, _id: 1}
+    }
+    ]).toArray().then(res => {
+            res.forEach(post => console.log(JSON.stringify(post)));
+        }).catch(err => {
+            console.log(err)
+        }).finally(() => {
+            db.close();
+        })
+});

desafiowebcrawler/desafiowebcrawler/queries_js/count_distinct_tags.js

@@ -0,0 +1,31 @@
+//Query para retornar o numero de tags recuperadas
+
+var MongoClient = require('mongodb').MongoClient;
+var url = "mongodb://localhost:27017/";
+
+MongoClient.connect(url, function(err, db) {
+    if (err) throw err;
+    var dbo = db.db("quotestoscrape");
+    dbo.collection('matheus_ferreira').aggregate([
+        {
+            "$unwind": "$tag"
+        },
+        {
+            "$group": {
+                "_id": "$tag",
+                "qtd": {
+                    "$sum": 1
+                }
+            }
+          },
+        {
+            "$sort": {qtd: -1, _id: 1}
+        }
+    ]).toArray().then(res => {
+        res.forEach(post => console.log(JSON.stringify(post)));
+    }).catch(err => {
+        console.log(err)
+    }).finally(() => {
+        db.close();
+    })
+});

desafiowebcrawler/desafiowebcrawler/queries_js/count_title.js

@@ -0,0 +1,16 @@
+//Query para retornar o numero de titulos recuperados
+
+var MongoClient = require('mongodb').MongoClient;
+var url = "mongodb://localhost:27017/";
+
+MongoClient.connect(url, function(err, db) {
+    if (err) throw err;
+    var dbo = db.db("quotestoscrape");
+    dbo.collection('matheus_ferreira').aggregate([
+    {
+        "$count": "title"
+    }]).toArray().then(function(result) {
+        console.log("A quantidade de citações é: " + result[0].title)
+    })
+});
+