From 03870c0eca405cd8c08253c8b07b93a9a9fadc44 Mon Sep 17 00:00:00 2001 From: Cody Hiar Date: Sun, 21 Mar 2021 13:14:53 -0600 Subject: Initial commit --- .gitignore | 12 +++ Makefile | 23 ++++++ README.md | 24 ++++++ docker-compose.yml | 14 ++++ docker/Dockerfile | 17 ++++ requirements.txt | 2 + web_grater/scrapy.cfg | 11 +++ web_grater/web_grater/__init__.py | 0 web_grater/web_grater/items.py | 14 ++++ web_grater/web_grater/middlewares.py | 103 +++++++++++++++++++++++++ web_grater/web_grater/pipelines.py | 11 +++ web_grater/web_grater/settings.py | 93 ++++++++++++++++++++++ web_grater/web_grater/spiders/__init__.py | 4 + web_grater/web_grater/spiders/grater_spider.py | 66 ++++++++++++++++ 14 files changed, 394 insertions(+) create mode 100644 .gitignore create mode 100644 Makefile create mode 100644 README.md create mode 100644 docker-compose.yml create mode 100644 docker/Dockerfile create mode 100644 requirements.txt create mode 100644 web_grater/scrapy.cfg create mode 100644 web_grater/web_grater/__init__.py create mode 100644 web_grater/web_grater/items.py create mode 100644 web_grater/web_grater/middlewares.py create mode 100644 web_grater/web_grater/pipelines.py create mode 100644 web_grater/web_grater/settings.py create mode 100644 web_grater/web_grater/spiders/__init__.py create mode 100644 web_grater/web_grater/spiders/grater_spider.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..a57a9ed --- /dev/null +++ b/.gitignore @@ -0,0 +1,12 @@ +.*.swp +*.pyc +*.pyo +.DS_Store +tags +.ropeproject +*.actual +.vimcache +.idea + +docker/requirements.txt +.mypy_cache diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..8a84b00 --- /dev/null +++ b/Makefile @@ -0,0 +1,23 @@ +.PHONY: build + +help: + @grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' + +build: ## Build the Docker image + cp requirements.txt docker/requirements.txt + docker-compose -p web_grater build + +up: build ## Bring the container up + docker-compose -p web_grater up -d + +down: ## Stop the container + docker-compose -p web_grater stop + +enter: ## Enter the running container + docker-compose -p web_grater exec backend /bin/bash + +clean: down ## Remove stoped containers + docker-compose -p web_grater rm + +crawl: ## Execute a crawl against a site + docker-compose -p web_grater exec backend /bin/bash -c 'cd web_grater && scrapy crawl grater' diff --git a/README.md b/README.md new file mode 100644 index 0000000..411a8d8 --- /dev/null +++ b/README.md @@ -0,0 +1,24 @@ +# Web Grater + +A very simple scrapy app for finding broken hrefs/images on your website. I've +used this on a number of website to help find broken content and hopefully it +can help you. + +## How do I use this? + +The project is dockerized but if don't want to use docker you can make a +virtualenv. First you need to update the site you want to crawl in +`web_grater/spiders/grater_spider.py`. After that you can just run: + +``` +make up && make crawl +``` + +This will print off all the urls the scraper can find and the broken ones in +red. + +## How do I find which page contains the broken link? + +In `grater_spider.py` there is a `CustomLinkExtractor` with a method called +`extract_links`. There is some commented out code that shows how you can search +for the broken link during link extraction and print the parent page in yellow. diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..1690296 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,14 @@ +version: '3' +services: + backend: + build: ./docker/ + network_mode: "bridge" + container_name: web_grater + image: thornycrackers/web_grater + ports: + - "8000" + volumes: + - .:/usr/src/app + command: /bin/bash + tty: true + stdin_open: true diff --git a/docker/Dockerfile b/docker/Dockerfile new file mode 100644 index 0000000..22e6328 --- /dev/null +++ b/docker/Dockerfile @@ -0,0 +1,17 @@ +FROM python:3.6 + +# Set the locale of the container +RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y locales +RUN sed -i -e 's/# en_US.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen && \ + dpkg-reconfigure --frontend=noninteractive locales && \ + update-locale LANG=en_US.UTF-8 +ENV LANG en_US.UTF-8 +ENV LANGUAGE en_US:en +ENV LC_ALL en_US.UTF-8 + +# Install Dependancies +COPY requirements.txt /opt/requirements.txt +RUN pip3 install -r /opt/requirements.txt + +# The code is stored here +WORKDIR /usr/src/app diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..4cf21c6 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,2 @@ +Scrapy==2.4.0 +blessings==1.6.1 diff --git a/web_grater/scrapy.cfg b/web_grater/scrapy.cfg new file mode 100644 index 0000000..fd9b643 --- /dev/null +++ b/web_grater/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 = web_grater.settings + +[deploy] +#url = http://localhost:6800/ +project = web_grater diff --git a/web_grater/web_grater/__init__.py b/web_grater/web_grater/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/web_grater/web_grater/items.py b/web_grater/web_grater/items.py new file mode 100644 index 0000000..3e08b63 --- /dev/null +++ b/web_grater/web_grater/items.py @@ -0,0 +1,14 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your scraped items +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class WebGraterItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/web_grater/web_grater/middlewares.py b/web_grater/web_grater/middlewares.py new file mode 100644 index 0000000..6f57985 --- /dev/null +++ b/web_grater/web_grater/middlewares.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your spider middleware +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +from scrapy import signals + + +class WebGraterSpiderMiddleware(object): + # 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, dict 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 Response, dict + # 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 WebGraterDownloaderMiddleware(object): + # 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/web_grater/web_grater/pipelines.py b/web_grater/web_grater/pipelines.py new file mode 100644 index 0000000..849e1d1 --- /dev/null +++ b/web_grater/web_grater/pipelines.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- + +# Define your item pipelines here +# +# Don't forget to add your pipeline to the ITEM_PIPELINES setting +# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html + + +class WebGraterPipeline(object): + def process_item(self, item, spider): + return item diff --git a/web_grater/web_grater/settings.py b/web_grater/web_grater/settings.py new file mode 100644 index 0000000..3dbd0ad --- /dev/null +++ b/web_grater/web_grater/settings.py @@ -0,0 +1,93 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for web_grater project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://doc.scrapy.org/en/latest/topics/settings.html +# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'web_grater' + +SPIDER_MODULES = ['web_grater.spiders'] +NEWSPIDER_MODULE = 'web_grater.spiders' + +LOG_LEVEL = 'INFO' + +HTTPERROR_ALLOW_ALL = True + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'web_grater (+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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'web_grater.middlewares.WebGraterSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'web_grater.middlewares.WebGraterDownloaderMiddleware': 543, +#} + +# Enable or disable extensions +# See https://doc.scrapy.org/en/latest/topics/extensions.html +#EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +#} + +# Configure item pipelines +# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html +#ITEM_PIPELINES = { +# 'web_grater.pipelines.WebGraterPipeline': 300, +#} + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://doc.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://doc.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' diff --git a/web_grater/web_grater/spiders/__init__.py b/web_grater/web_grater/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/web_grater/web_grater/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/web_grater/web_grater/spiders/grater_spider.py b/web_grater/web_grater/spiders/grater_spider.py new file mode 100644 index 0000000..a8780d6 --- /dev/null +++ b/web_grater/web_grater/spiders/grater_spider.py @@ -0,0 +1,66 @@ +# -*- coding: utf-8 -*- +"""Grater Spider for parsing urls.""" +from typing import Generator + +from blessings import Terminal +from scrapy.http import Request +from scrapy.http.response.html import HtmlResponse +from scrapy.linkextractors import LinkExtractor +from scrapy.spiders import Spider + +t = Terminal() + +# The site you want to crawl +WEBSITE = "www.example.com" + + +class CustomLinkExtractor(LinkExtractor): + """Custom extractor for checking results.""" + + def extract_links(self, response): + """Get links from a page. + + If you run the scraper and find that there is a url that is broken + and you want to know which page it was on you can uncomment and upate + the term below so that it will print pages containing that link in + yellow so you can find them + """ + links = super().extract_links(response) + # for link in links: + # if 'insert-search-term-here' in link.url: + # print(f'{t.yellow}200 Page: {response.url}{t.normal}') + return links + + +class GraterSpider(Spider): + """Grater Spider.""" + + name = "grater" + allowed_domains = [f"{WEBSITE}"] + start_urls = [f"https://{WEBSITE}"] + + def __init__(self, *args, **kwargs): + """Init custom link extractor.""" + self.link_extractor = CustomLinkExtractor() + return super().__init__(*args, **kwargs) + + def parse(self, response: HtmlResponse) -> Generator: + """Parse a page.""" + if response.status == 200: + print(f"{t.green}200 Page: {response.url}{t.normal}") + else: + print(f"{t.red}{response.status} Page: {response.url}{t.normal}") + # Parse all links on the current page + for link in self.link_extractor.extract_links(response): + yield Request(link.url, callback=self.parse) + # Parse all the images + img_urls = response.css("img::attr(src)").extract() + for img_url in img_urls: + yield response.follow(img_url, callback=self.parse_image_request) + + def parse_image_request(self, response: HtmlResponse) -> None: + """Parse the request for an image.""" + if response.status == 200: + print(f"{t.green}200 Image: {response.url}{t.normal}") + else: + print(f"{t.red}{response.status} Image: {response.url}{t.normal}") -- cgit v1.2.3