chair网站爬虫

claie_crawler/items.py

+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ClaieCrawlerItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

claie_crawler/middlewares.py

+# 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 ClaieCrawlerSpiderMiddleware:
+    # 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 ClaieCrawlerDownloaderMiddleware:
+    # 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)

claie_crawler/pipelines.py

+# 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 ClaieCrawlerPipeline:
+    def process_item(self, item, spider):
+        return item

claie_crawler/settings.py

+# Scrapy settings for claie_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 = "claie_crawler"
+
+SPIDER_MODULES = ["claie_crawler.spiders"]
+NEWSPIDER_MODULE = "claie_crawler.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "claie_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 = {
+#    "claie_crawler.middlewares.ClaieCrawlerSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "claie_crawler.middlewares.ClaieCrawlerDownloaderMiddleware": 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 = {
+#    "claie_crawler.pipelines.ClaieCrawlerPipeline": 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"

claie_crawler/spiders/__init__.py

+# 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.

claie_crawler/spiders/claie.py

+import scrapy
+from urllib.parse import urljoin
+import os
+import pdfkit
+
+class ClaieSpider(scrapy.Spider):
+    name = 'claie'
+    allowed_domains = ['claie.org']
+    start_urls = ['https://www.claie.org/']
+
+    #path_wkhtmltopdf = '/usr/local/bin/wkhtmltopdf'  # 对于 MacOS/Linux
+    path_wkhtmltopdf = r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe'  # 对于 Windows
+    config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
+
+    def parse(self, response):
+        # 提取页面内容，但过滤掉特定段落
+        unwanted_texts = [
+            '关于我们', '法律声明', '下载中心', '联系我们',
+            '支持：北京大学', '中国人民大学', '中国通用航空发展协会', '中国直升机产业发展协会', '欧美同学会企业家联谊会',
+            '协办：领导干部国学大讲堂 曲阜儒商会馆管理有限公司',
+            '版权所有：中国低空产业经济研究院 国城弦歌（北京）文化传播中心',
+            'http://claie.org', 'E-mail:907421288@qq.com',
+            '首页', '政策法规', '产业动态', '产业经济', '航校培训', '生产基地',
+            '维护租赁', '销售物流', '产业咨询', '产业案例', '园区规划', '应急救援',
+            '医疗救援', '消防救援', '农药喷洒', '海上救援', '地震救援', '俱乐部'
+        ]
+        
+        page_title = response.css('title::text').get()
+        all_texts = response.css('body *::text').getall()
+        
+        # 过滤掉包含不需要内容的文本
+        page_content = ' '.join([
+            text.strip() for text in all_texts
+            if not any(unwanted in text for unwanted in unwanted_texts)
+        ])
+
+        # 保存页面内容为PDF
+        self.save_page_as_pdf(response.url, page_title, page_content)
+
+        # 提取所有链接并递归爬取
+        for href in response.css('a::attr(href)').extract():
+            url = urljoin(response.url, href)
+            if self.allowed_domains[0] in url:
+                yield scrapy.Request(url, callback=self.parse)
+
+    def save_page_as_pdf(self, url, title, content):
+        # 创建一个文件夹来保存爬取的内容
+        directory = 'downloaded_pages_pdf'
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+
+        # 创建临时HTML文件
+        html_content = f"""
+        <html>
+        <head>
+            <meta charset="utf-8">
+            <title>{title}</title>
+        </head>
+        <body>
+            <h1>{title}</h1>
+            <p><a href="{url}">{url}</a></p>
+            <p>{content}</p>
+        </body>
+        </html>
+        """
+
+        # 创建文件名
+        filename = os.path.join(directory, f"{title[:50].strip().replace(' ', '_').replace('/', '_')}.pdf")
+        
+        path_wkhtmltopdf = r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe'  # 对于 Windows
+        config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
+
+        # 使用pdfkit保存为PDF文件
+        pdfkit.from_string(html_content, filename)
+        self.log(f'Saved page as PDF {filename}')

claie_crawler/spiders/scheduled_spider.py

+import datetime
+from apscheduler.schedulers.background import BackgroundScheduler
+import os
+import pdfkit
+import scrapy
+from scrapy.crawler import CrawlerProcess
+from scrapy.utils.project import get_project_settings
+from urllib.parse import urljoin
+
+class ClaieSpider(scrapy.Spider):
+    name = 'claie'
+    allowed_domains = ['claie.org']
+    start_urls = ['https://www.claie.org/']
+
+    path_wkhtmltopdf = r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe'  # 对于 Windows
+    config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
+
+
+    # path_wkhtmltopdf = '/usr/local/bin/wkhtmltopdf'  # 对于 Linux
+    # config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
+
+    def parse(self, response):
+        unwanted_texts = [
+            '关于我们', '法律声明', '下载中心', '联系我们',
+            '支持：北京大学', '中国人民大学', '中国通用航空发展协会', '中国直升机产业发展协会', '欧美同学会企业家联谊会',
+            '协办：领导干部国学大讲堂 曲阜儒商会馆管理有限公司',
+            '版权所有：中国低空产业经济研究院 国城弦歌（北京）文化传播中心',
+            'http://claie.org', 'E-mail:907421288@qq.com',
+            '首页', '政策法规', '产业动态', '产业经济', '航校培训', '生产基地',
+            '维护租赁', '销售物流', '产业咨询', '产业案例', '园区规划', '应急救援',
+            '医疗救援', '消防救援', '农药喷洒', '海上救援', '地震救援', '俱乐部'
+        ]
+        
+        page_title = response.css('title::text').get()
+        all_texts = response.css('body *::text').getall()
+        
+        page_content = ' '.join([
+            text.strip() for text in all_texts
+            if not any(unwanted in text for unwanted in unwanted_texts)
+        ])
+
+        self.save_page_as_pdf(response.url, page_title, page_content)
+
+        for href in response.css('a::attr(href)').extract():
+            url = urljoin(response.url, href)
+            if self.allowed_domains[0] in url:
+                yield scrapy.Request(url, callback=self.parse)
+
+    def save_page_as_pdf(self, url, title, content):
+        directory = 'downloaded_pages_pdf'
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+        
+        html_content = f"""
+        <html>
+        <head>
+            <meta charset="utf-8">
+            <title>{title}</title>
+        </head>
+        <body>
+            <h1>{title}</h1>
+            <p><a href="{url}">{url}</a></p>
+            <p>{content}</p>
+        </body>
+        </html>
+        """
+
+        filename = os.path.join(directory, f"{title[:50].strip().replace(' ', '_').replace('/', '_')}.pdf")
+        config = pdfkit.configuration(wkhtmltopdf=self.path_wkhtmltopdf)
+
+        pdfkit.from_string(html_content, filename, configuration=config)
+        self.log(f'Saved page as PDF {filename}')
+
+class TaskScheduler:
+    def __init__(self):
+        self.scheduler = BackgroundScheduler()
+
+    def add_task(self, timedTask):
+        # 使用 cron 触发器每天凌晨2点执行任务
+        self.scheduler.add_job(timedTask, 'cron', hour=9, minute=46)
+
+    def start_scheduler(self):
+        self.scheduler.start()
+
+    def stop_scheduler(self):
+        self.scheduler.shutdown()
+
+def run_spider():
+    process = CrawlerProcess(get_project_settings())
+    process.crawl(ClaieSpider)
+    process.start()
+
+if __name__ == "__main__":
+    scheduler = TaskScheduler()
+    scheduler.add_task(run_spider)  # 每天早晨10点执行一次爬虫
+    scheduler.start_scheduler()
+    try:
+        while True:
+            pass
+    except KeyboardInterrupt:
+        scheduler.stop_scheduler()