Pull Request para finalizar o desafio

.env.dist

@@ -0,0 +1,5 @@
+DATABASE_USERNAME=
+DATABASE_PASSWORD=
+DATABASE_PORT=27017
+DATABASE_HOST=localhost
+DATABASE_NAME=quotestoscrape

.gitignore

@@ -0,0 +1,3 @@
+.venv
+*.pyc
+.env

docker-compose.yml

@@ -0,0 +1,36 @@
+version: '3.9'
+
+services:
+  mongodb:
+    container_name: mongodb
+    image: mongo:latest
+    restart: always
+    ports:
+      - $DATABASE_PORT:$DATABASE_PORT
+    networks:
+      - mongo-compose-network
+    volumes:
+      - ./queries/:/queries
+      - ~/apps/mongo:/data/db
+    environment:
+      - MONGO_INITDB_ROOT_USERNAME=$DATABASE_USERNAME
+      - MONGO_INITDB_ROOT_PASSWORD=$DATABASE_PASSWORD
+
+  mongo-express:
+    container_name: mongo-express
+    image: mongo-express:latest
+    restart: always
+    depends_on:
+      - mongodb
+    ports:
+      - 8081:8081
+    networks:
+      - mongo-compose-network
+    environment:
+      ME_CONFIG_MONGODB_ADMINUSERNAME: $DATABASE_USERNAME
+      ME_CONFIG_MONGODB_ADMINPASSWORD: $DATABASE_PASSWORD
+      ME_CONFIG_MONGODB_URL: mongodb://$DATABASE_USERNAME:$DATABASE_PASSWORD@mongodb:$DATABASE_PORT
+
+networks:
+  mongo-compose-network:
+    driver: bridge

queries/citations_collected.js

@@ -0,0 +1,10 @@
+result = db.jovane_mafort.aggregate(
+    [
+        // Count how many documents are inside the collection
+        {
+            $count: "number_of_citations_collected"
+        }
+    ]
+).toArray();
+
+printjson(result);

queries/citations_per_author.js

@@ -0,0 +1,14 @@
+result = db.jovane_mafort.aggregate(
+    [
+        // Groups and counts the documents by the name of each author
+        {
+            $group: { _id: "$author.name", quantity: { $count: {} } }
+        },
+        // Sort results by number of occurrences, descending
+        {
+            $sort: { quantity: -1}
+        }
+    ]
+).toArray();
+
+printjson(result);

queries/citations_per_tag.js

@@ -0,0 +1,18 @@
+result = db.jovane_mafort.aggregate(
+    [
+        // Deconstructs the tags array field
+        {
+            $unwind: "$tags",
+        },
+        // Group and counts the documents by each unique tag 
+        {
+            $group: { _id:"$tags", quantity: { $count: {} } }
+        },
+        // Sort results by number of occurrences, descending
+        {
+            $sort: { quantity: -1 } 
+        }
+    ]
+).toArray();
+
+printjson(result)

queries/distinct_tags.js

@@ -0,0 +1,18 @@
+result = db.jovane_mafort.aggregate(
+    [
+        // Deconstructs the tags array field
+        {
+            $unwind: "$tags"
+        },
+        // Group the documents by tags
+        {
+            $group: {_id: "$tags"}
+        },
+        // Counts the number of unique tags
+        {
+            $count: "number_of_distinct_tags"
+        }
+    ]
+).toArray();
+
+printjson(result);

webcrawler/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 = webcrawler.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = webcrawler

webcrawler/webcrawler/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 WebcrawlerItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

webcrawler/webcrawler/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 WebcrawlerSpiderMiddleware:
+    # 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 WebcrawlerDownloaderMiddleware:
+    # 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)

webcrawler/webcrawler/pipelines.py

@@ -0,0 +1,41 @@
+# 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 WebcrawlerPipeline:
+    def process_item(self, item, spider):
+        return item
+
+
+class MongoPipeline:
+
+    collection_name = 'jovane_mafort'
+
+    def __init__(self, mongo_uri, mongo_db):
+        self.mongo_uri = mongo_uri
+        self.mongo_db = mongo_db
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls(
+            mongo_uri=crawler.settings.get('MONGO_URI'),
+            mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
+        )
+
+    def open_spider(self, spider):
+        self.client = pymongo.MongoClient(self.mongo_uri)
+        self.db = self.client[self.mongo_db]
+
+    def close_spider(self, spider):
+        self.client.close()
+
+    def process_item(self, item, spider):
+        self.db[self.collection_name].insert_one(ItemAdapter(item).asdict())
+        return item

webcrawler/webcrawler/settings.py

@@ -0,0 +1,102 @@
+# Scrapy settings for webcrawler 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
+
+import os
+
+import dotenv
+
+
+dotenv.load_dotenv()
+
+BOT_NAME = 'webcrawler'
+
+SPIDER_MODULES = ['webcrawler.spiders']
+NEWSPIDER_MODULE = 'webcrawler.spiders'
+
+USERNAME = os.getenv('DATABASE_USERNAME')
+PASSWORD = os.getenv('DATABASE_PASSWORD')
+PORT = os.getenv('DATABASE_PORT')
+HOST = os.getenv('DATABASE_HOST')
+MONGO_URI = f'mongodb://{USERNAME}:{PASSWORD}@{HOST}:{PORT}'
+MONGO_DATABASE = os.getenv('DATABASE_NAME')
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'webcrawler (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# 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 = {
+#    'webcrawler.middlewares.WebcrawlerSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'webcrawler.middlewares.WebcrawlerDownloaderMiddleware': 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 = {
+   'webcrawler.pipelines.WebcrawlerPipeline': 300,
+   'webcrawler.pipelines.MongoPipeline': 0
+}
+
+# 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'

webcrawler/webcrawler/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.