From 50f2efd8861fa2bae7c1231acb57428063cea7a7 Mon Sep 17 00:00:00 2001 From: Jourdelune Date: Wed, 5 Jun 2024 21:29:14 +0200 Subject: [PATCH] [update] add scrapy --- Crawler/__init__.py | 0 Crawler/items.py | 12 ++++ Crawler/middlewares.py | 103 +++++++++++++++++++++++++++++++ Crawler/pipelines.py | 13 ++++ Crawler/settings.py | 93 ++++++++++++++++++++++++++++ Crawler/spiders/__init__.py | 4 ++ Crawler/spiders/quotes_spider.py | 11 ++++ README.md | 18 ++++++ requirements.txt | 2 +- scrapy.cfg | 11 ++++ 10 files changed, 266 insertions(+), 1 deletion(-) create mode 100644 Crawler/__init__.py create mode 100644 Crawler/items.py create mode 100644 Crawler/middlewares.py create mode 100644 Crawler/pipelines.py create mode 100644 Crawler/settings.py create mode 100644 Crawler/spiders/__init__.py create mode 100644 Crawler/spiders/quotes_spider.py create mode 100644 scrapy.cfg diff --git a/Crawler/__init__.py b/Crawler/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/Crawler/items.py b/Crawler/items.py new file mode 100644 index 0000000..b3d39d6 --- /dev/null +++ b/Crawler/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 CrawlerItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/Crawler/middlewares.py b/Crawler/middlewares.py new file mode 100644 index 0000000..8129bad --- /dev/null +++ b/Crawler/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 CrawlerSpiderMiddleware: + # 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 CrawlerDownloaderMiddleware: + # 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) diff --git a/Crawler/pipelines.py b/Crawler/pipelines.py new file mode 100644 index 0000000..e3aa1dc --- /dev/null +++ b/Crawler/pipelines.py @@ -0,0 +1,13 @@ +# 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 + + +class CrawlerPipeline: + def process_item(self, item, spider): + return item diff --git a/Crawler/settings.py b/Crawler/settings.py new file mode 100644 index 0000000..16e9c32 --- /dev/null +++ b/Crawler/settings.py @@ -0,0 +1,93 @@ +# Scrapy settings for Crawler 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 = "Crawler" + +SPIDER_MODULES = ["Crawler.spiders"] +NEWSPIDER_MODULE = "Crawler.spiders" + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = "Crawler (+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 = { +# "Crawler.middlewares.CrawlerSpiderMiddleware": 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# "Crawler.middlewares.CrawlerDownloaderMiddleware": 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 = { +# "Crawler.pipelines.CrawlerPipeline": 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 +REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7" +TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor" +FEED_EXPORT_ENCODING = "utf-8" diff --git a/Crawler/spiders/__init__.py b/Crawler/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/Crawler/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. diff --git a/Crawler/spiders/quotes_spider.py b/Crawler/spiders/quotes_spider.py new file mode 100644 index 0000000..ccad2a6 --- /dev/null +++ b/Crawler/spiders/quotes_spider.py @@ -0,0 +1,11 @@ +from pathlib import Path + +import scrapy + + +class AudiosSpider(scrapy.Spider): + name = "audios" + start_urls = [] + + def parse(self, response): + pass diff --git a/README.md b/README.md index bbce1b1..f4a5e78 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,20 @@ # Crawler The crawler for WaveGenAI + +## Setup + +1. Install the required packages +```bash +pip install -r requirements.txt +``` + +## Usage + +Run the crawler +```bash +scrapy crawl audios +``` + +## License + +This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details \ No newline at end of file diff --git a/requirements.txt b/requirements.txt index 8b13789..268b0db 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1 +1 @@ - +scrapy diff --git a/scrapy.cfg b/scrapy.cfg new file mode 100644 index 0000000..32522de --- /dev/null +++ b/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 = Crawler.settings + +[deploy] +#url = http://localhost:6800/ +project = Crawler