Browse Source

init spider

master
Lennart Weller 2 weeks ago
commit
25ba8380e2
  1. 136
      .gitignore
  2. 0
      gardenersworld/__init__.py
  3. 12
      gardenersworld/items.py
  4. 103
      gardenersworld/middlewares.py
  5. 13
      gardenersworld/pipelines.py
  6. 88
      gardenersworld/settings.py
  7. 4
      gardenersworld/spiders/__init__.py
  8. 36
      gardenersworld/spiders/hdclump.py
  9. 2
      requirements.txt
  10. 11
      scrapy.cfg

136
.gitignore

@ -0,0 +1,136 @@
# 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/
# Visual Studio Code
.vscode
# 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/
# project specific
*.asc
*.json

0
gardenersworld/__init__.py

12
gardenersworld/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 GardenersworldItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass

103
gardenersworld/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 GardenersworldSpiderMiddleware:
# 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 GardenersworldDownloaderMiddleware:
# 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)

13
gardenersworld/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 GardenersworldPipeline:
def process_item(self, item, spider):
return item

88
gardenersworld/settings.py

@ -0,0 +1,88 @@
# Scrapy settings for gardenersworld 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 = 'gardenersworld'
SPIDER_MODULES = ['gardenersworld.spiders']
NEWSPIDER_MODULE = 'gardenersworld.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'gardenersworld (+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 = {
# 'gardenersworld.middlewares.GardenersworldSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'gardenersworld.middlewares.GardenersworldDownloaderMiddleware': 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 = {
# 'gardenersworld.pipelines.GardenersworldPipeline': 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'

4
gardenersworld/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.

36
gardenersworld/spiders/hdclump.py

@ -0,0 +1,36 @@
from datetime import datetime
import re
from scrapy.spiders import SitemapSpider
from scrapy.linkextractors import LinkExtractor
class HDClumpSitemapSpider(SitemapSpider):
name = "hdclump_sitemap_spider"
allowed_domains = ["hdclump.com"]
sitemap_urls = ["https://hdclump.com/sitemap.xml"]
sitemap_rules = [("/gardeners-world.*?/", "parse_garden")]
def sitemap_filter(self, entries):
for entry in entries:
date_time = datetime.strptime(
entry.get("lastmod", "1970-01-01T00:00:00Z"), "%Y-%m-%dT%H:%M:%SZ"
)
if date_time.year >= datetime.now().year:
link = entry.get("loc", "")
if "special" in link:
continue
if "sitemap" in link or str(datetime.now().year) in link:
yield entry
def parse_garden(self, response):
link_extractor = LinkExtractor(allow_domains=["dailymotion.com", "ok.ru", "bitchute.com"])
title = response.xpath("//h2[contains(@itemprop,'headline')]/text()").get()
year = int(re.search('\d{4}', title).group(0))
episode = int(re.search('episode (\d{,2})', title, flags=re.IGNORECASE).group(1))
yield {
"year": year,
"episode": episode,
"links": [x.url for x in link_extractor.extract_links(response)],
"source": response.url
}

2
requirements.txt

@ -0,0 +1,2 @@
scrapy
git+https://github.com/lucasnobre212/scrapyd-client.git

11
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 = gardenersworld.settings
[deploy]
url = https://scrapyd.hh.wellr.net/
project = gardenersworld
Loading…
Cancel
Save