diff --git a/NO45/scrapy.cfg b/NO45/scrapy.cfg new file mode 100644 index 0000000000000000000000000000000000000000..7d9e63b690f4406da46e39990a1e32ba7ff9114a --- /dev/null +++ b/NO45/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 = yuewen.settings + +[deploy] +#url = http://localhost:6800/ +project = yuewen diff --git a/NO45/yuewen/__init__.py b/NO45/yuewen/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/NO45/yuewen/__pycache__/__init__.cpython-37.pyc b/NO45/yuewen/__pycache__/__init__.cpython-37.pyc new file mode 100644 index 0000000000000000000000000000000000000000..352f7e7f3a69f0aa104005137d300547e384109d Binary files /dev/null and b/NO45/yuewen/__pycache__/__init__.cpython-37.pyc differ diff --git a/NO45/yuewen/__pycache__/settings.cpython-37.pyc b/NO45/yuewen/__pycache__/settings.cpython-37.pyc new file mode 100644 index 0000000000000000000000000000000000000000..38ac59b39e4cc753817649eac329245b46d7d99d Binary files /dev/null and b/NO45/yuewen/__pycache__/settings.cpython-37.pyc differ diff --git a/NO45/yuewen/items.py b/NO45/yuewen/items.py new file mode 100644 index 0000000000000000000000000000000000000000..5addc6d6cf292544f5bdcd790be6928124872cdf --- /dev/null +++ b/NO45/yuewen/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 YuewenItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/NO45/yuewen/middlewares.py b/NO45/yuewen/middlewares.py new file mode 100644 index 0000000000000000000000000000000000000000..c8da86a5c5782eab131e4b5f4ed26fb00d196aa3 --- /dev/null +++ b/NO45/yuewen/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 YuewenSpiderMiddleware: + # 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 YuewenDownloaderMiddleware: + # 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/NO45/yuewen/pipelines.py b/NO45/yuewen/pipelines.py new file mode 100644 index 0000000000000000000000000000000000000000..db7958bfbe918041df386439572f4a6efa49e5a9 --- /dev/null +++ b/NO45/yuewen/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 YuewenPipeline: + def process_item(self, item, spider): + return item diff --git a/NO45/yuewen/settings.py b/NO45/yuewen/settings.py new file mode 100644 index 0000000000000000000000000000000000000000..371cbd634901e1b6be72de3499a287a9accf8ca2 --- /dev/null +++ b/NO45/yuewen/settings.py @@ -0,0 +1,89 @@ +# Scrapy settings for yuewen 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 = 'yuewen' + +SPIDER_MODULES = ['yuewen.spiders'] +NEWSPIDER_MODULE = 'yuewen.spiders' + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'yuewen (+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://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 = { +# 'yuewen.middlewares.YuewenSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'yuewen.middlewares.YuewenDownloaderMiddleware': 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 = { +# 'yuewen.pipelines.YuewenPipeline': 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' +LOG_LEVEL = 'WARNING' diff --git a/NO45/yuewen/spiders/__init__.py b/NO45/yuewen/spiders/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..ebd689ac51d69c5e1dbbe80083c2b20a39f8bb79 --- /dev/null +++ b/NO45/yuewen/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/NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc b/NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc new file mode 100644 index 0000000000000000000000000000000000000000..149125917c57e784ca09836f816d436ded7990e5 Binary files /dev/null and b/NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc differ diff --git a/NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc b/NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f9a35912012722e95a7629c504cd93e584c6414b Binary files /dev/null and b/NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc differ diff --git a/NO45/yuewen/spiders/yw.py b/NO45/yuewen/spiders/yw.py new file mode 100644 index 0000000000000000000000000000000000000000..a3205b5c5fc4444bc95425394325760e4cb7069e --- /dev/null +++ b/NO45/yuewen/spiders/yw.py @@ -0,0 +1,34 @@ +import scrapy +from scrapy.linkextractors import LinkExtractor +from scrapy.spiders import CrawlSpider, Rule + + +class CbSpider(CrawlSpider): + name = 'yw' + allowed_domains = ['write.qq.com'] + start_urls = ['https://write.qq.com/portal/article?filterType=0&page=1'] + # URL 提取规则 + rules = ( + Rule(LinkExtractor(allow=r'.*/portal/content\?caid=\d+&feedType=2&lcid=\d+$'), callback="parse_item"), + # 寻找下一页 url 地址 + Rule(LinkExtractor(restrict_xpaths="//a[@title='下一页']"), follow=True), + ) + + def parse_start_url(self, response): + print("---process_results---") + yield scrapy.Request('https://write.qq.com/portal/article?filterType=0&page=1') + + def process_results(self, response, results): + print("---process_results---") + print(results) + + def parse_item(self, response): + print("---parse_item---") + print(response.url) + title = response.css('title::text').extract()[0].strip() + item = {} + item["title"] = title + yield item + + def parse(self): + pass \ No newline at end of file diff --git a/README.md b/README.md index 169ec4ee93a4b14b82db1628e8542678cb086035..3ebcbc2c1e76619f70be45f344708b3c95287df2 100644 --- a/README.md +++ b/README.md @@ -85,5 +85,8 @@ ### 📘 scrapy 库学习 - +42. [学python，怎么能不学习scrapy呢，这篇博客带你学会它](https://dream.blog.csdn.net/article/details/120899494) +43. [python scrapy 管道学习，并拿在行练手爬虫项目](https://dream.blog.csdn.net/article/details/120934425) +44. [python scrapy极细拆解，打开Spider类看内容，顺手爬了一下优设网](https://dream.blog.csdn.net/article/details/120936534) +45. [练手练到阅文集团作家中心了，python crawlspider 二维抓取学习](https://dream.blog.csdn.net/article/details/120835220)