init

Author: Andryas

.gitignore

@@ -0,0 +1,16 @@
+gaia/
+bkb/
+.DS_Store
+venv/
+.vscode/
+.scrapy/
+dev/
+__pycache__/
+.env
+dump/
+credentials.json
+R/
+pipeline/
+achieve/
+waurzenczak.json
+andryas.json

README.md

@@ -0,0 +1,17 @@
+# Quick tutorial for scraping with GCP with no database
+
+Long story short, the idea is to schedule a machine to start and die after webscraping. To avoid having a database, we create a JSON and insert which page crawled inside this json, and after it finishes collecting, we send it to the bucket. 
+
+- create a VM
+- create a schedule for the VM usign crontab
+- create a bucket, get this bucket name and use in the next step
+- create a file .env in this repository and set BUCKET=bucket-name
+- send this repository to the vm,
+  - sudo bash setup.sh
+  - config crontab, for instance, `15 12 * * MON bash /home/wavrzenczak/scraping/crawl.sh test`
+- Note that the crontab for schedule machine need to be close to the crontab setting in the VM, I'd put 15 minutes from each other just in case.
+
+Now, see how is create the `src/spiders/test.py`,  create another one following
+the structure, `pipeline.py`, and be happy.
+
+

connect.sh

@@ -0,0 +1 @@
+gcloud compute ssh --zone "us-central1-c" "scraping" --project "waurzenczak"

crawl.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+cd /home/wavrzenczak/scraping
+source venv/bin/activate
+
+# get the start date and time
+start_datetime=$(date '+%m_%d_%Y_%H_%M_%S')
+echo "${start_datetime} - starting spider"
+
+# prevent click, which pipenv relies on, from freaking out to due to lack of locale info https://click.palletsprojects.com/en/7.x/python3/
+export LC_ALL=en_US.utf-8
+
+scrapy crawl $1
+
+# -a debug=$DEBUG &> "logs/log_${start_datetime}.txt"
+# get the end date and time
+end_datetime=$(date '+%m_%d_%Y_%H_%M_%S')
+echo "${end_datetime} - spider finished successfully"
+root shutdown

deploy.sh

@@ -0,0 +1,4 @@
+
+rsync -rv --exclude=.gitignore --exclude=.git --exclude=.vscode --exclude=venv/ . scraping/ 
+gcloud compute scp --recurse scraping/ scraping:/home/wavrzenczak/scraping --zone us-central1-c
+sudo rm -rf scraping/

requirements.txt

@@ -0,0 +1,21 @@
+wheel
+Scrapy==2.6.2
+scrapy-splash==0.8.0
+scrapy-user-agents==0.1.1
+
+python-dotenv==0.19.2
+python-decouple==3.0
+
+lxml==4.9.1
+requests==2.28.1
+
+pyopenssl==22.0.0
+cryptography==36.0.0
+dateparser==1.1.2
+unidecode==1.3.4
+
+psycopg2-binary==2.9.5
+random_user_agent==1.0.1
+
+jsonlines==3.1.0
+google-cloud-storage

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

setup.sh

@@ -0,0 +1,9 @@
+apt update && apt upgrade
+# apt -y install python3-venv
+apt -y install python3.9
+apt -y install python3.9-venv
+# apt -y install python3-virtualenv
+# apt -y install python3 python3-pip
+virtualenv -p python3.9 venv
+source venv/bin/activate
+pip install -r requirements.txt

src/__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.

src/middlewares.py

@@ -0,0 +1,102 @@
+# -*- 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 ScrSpiderMiddleware(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 ScrDownloaderMiddleware(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)

src/pipeline.py

@@ -0,0 +1,26 @@
+import json
+from itemadapter import ItemAdapter
+from src.utils.gcp import *
+from src.utils.destymd import destymd
+from src.settings import *
+
+class JsonWriterPipeline:
+
+    def __init__(self):
+        pass
+
+    def open_spider(self, spider):
+        self.file = open(spider.name + ".jsonl", "w")
+
+    def close_spider(self, spider):
+        self.file.close()
+        upload_blob(
+            BUCKET, 
+            spider.name + ".jsonl",
+            destymd(spider.name, "jsonl")
+        )
+
+    def process_item(self, item, spider):
+        line = json.dumps(ItemAdapter(item).asdict()) + "\n"
+        self.file.write(line)
+        return item

src/settings.py

@@ -0,0 +1,103 @@
+from dotenv import load_dotenv
+from os import getenv
+
+load_dotenv()
+
+BUCKET = getenv("BUCKET")
+
+BOT_NAME = 'src'
+
+SPIDER_MODULES = ['src.spiders']
+NEWSPIDER_MODULE = 'src.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'scr (+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 = 0.25
+# The download delay setting will honor only one of:
+CONCURRENT_REQUESTS_PER_DOMAIN = 32
+
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = True
+
+# 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 = {
+#    'scr.middlewares.ScrSpiderMiddleware': 543,
+#}
+DOWNLOAD_HANDLERS = {
+    'http': 'scrapy.core.downloader.handlers.http.HTTPDownloadHandler',
+    'https': 'scrapy.core.downloader.handlers.http.HTTPDownloadHandler',
+    'ftp': None,
+    'file': None,
+    's3': None
+}
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+  'scrapy_splash.SplashCookiesMiddleware': 720,
+  'scrapy_splash.SplashMiddleware': 730,
+  'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+  
+  # USER-AGENT
+  'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
+  'scrapy_user_agents.middlewares.RandomUserAgentMiddleware': 400,
+}
+
+# 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 = {
+#     'src.pipelines.Pipeline': 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 = 2
+# The maximum download delay to be set in case of high latencies
+AUTOTHROTTLE_MAX_DELAY = 20
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+AUTOTHROTTLE_TARGET_CONCURRENCY = 20
+# 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 = False
+HTTPCACHE_EXPIRATION_SECS = 0
+HTTPCACHE_DIR = 'httpcache'
+HTTPCACHE_IGNORE_HTTP_CODES = []
+HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
+
+# FEEDS = {
+#     'data.json': {'format': 'json', 'overwrite': True}
+#     # 'data.jsonl': {'format': 'jsonlines', 'overwrite': True}
+# }

src/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.

src/spiders/test.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+from src.settings import *
+from src.utils.lubridate import now
+
+class TestGCPSpider(scrapy.Spider):
+    name = 'test_gcp'
+
+    custom_settings = {
+        'ITEM_PIPELINES': {
+            'src.pipeline.JsonWriterPipeline': 300
+        }
+    }
+
+    def start_requests(self):
+        urls = [
+            'https://quotes.toscrape.com/page/1/',
+        ]
+        for url in urls:
+            yield scrapy.Request(url=url, callback=self.parse)
+
+    def parse(self, response):
+        for quote in response.css('div.quote'):
+            yield {
+                'created_at': now(False),
+                'text': quote.css('span.text::text').get(),
+                'author': quote.css('small.author::text').get(),
+                'tags': quote.css('div.tags a.tag::text').getall()
+            }
+
+       
+
+       

src/utils/__init__.py

@@ -0,0 +1,5 @@
+# https://www.codegrepper.com/code-examples/python/split+a+list+in+100+each
+def chunks(lst, n):
+    """Yield successive n-sized chunks from lst."""
+    for i in range(0, len(lst), n):
+        yield lst[i:i + n]