first commit

.gitignore

@@ -0,0 +1,4 @@
+dbs/*
+venv/*
+__pycache__/
+*.pyc

note.txt

@@ -0,0 +1 @@
+scrapy crawl basespider -a start_url=http://ctc.ac.cn/

requirements.txt

@@ -0,0 +1,3 @@
+scrapy==2.8.0
+scrapyd==1.4.1
+scrapyd-client==1.2.3

scrapy.cfg

@@ -0,0 +1,14 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = zcspider.settings
+
+[scrapyd]
+bind_address = 0.0.0.0
+
+[deploy zc1]
+# url = http://localhost:6800/
+project = zcspider

zcspider/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 ZcspiderItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

zcspider/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 ZcspiderSpiderMiddleware:
+    # 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 ZcspiderDownloaderMiddleware:
+    # 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)

zcspider/pipelines.py

@@ -0,0 +1,45 @@
+# 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 scrapy.exceptions import IgnoreRequest
+import psycopg2
+
+class ZcspiderPipeline:
+
+    def open_spider(self, spider):
+        print('初始化数据库连接')
+        self.conn = psycopg2.connect(host="49.232.14.174",database="zcspider", user="postgres", password="zcDsj2021")
+        self.cur = self.conn.cursor()
+        self.cur.execute("delete from content where domain = %s", (spider.domain, ))
+        # rows = self.cur.fetchall()
+        # spider.visited_urls_last = [i[0] for i in rows] if len(rows)>1 else []
+    
+    # def process_request(self, request, spider):
+    #     print('检查当前地址有没有存储过')
+    #     self.cur.execute("SELECT url from content where url= %s", request.url)
+    #     row = self.cur.fetchone() is not None
+    #     print(row)
+    #     if row:
+    #         raise IgnoreRequest(f"Duplicate URL found: {request.url}")
+    #     return request
+
+    def process_item(self, item, spider):
+        try:
+            self.cur.execute("INSERT INTO content (domain, url, text) VALUES(%s, %s, %s)",
+                            (item['domain'], item['url'], item['text']))
+            self.conn.commit()
+        except:
+            self.conn.rollback()
+            raise
+        return item
+
+    # 结束，关闭连接
+    def close_spider(self, spider):
+        # 关闭游标
+        self.cur.close()
+        # 关闭连接
+        self.conn.close()

zcspider/settings.py

@@ -0,0 +1,97 @@
+# Scrapy settings for zcspider 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 = "zcspider"
+
+SPIDER_MODULES = ["zcspider.spiders"]
+NEWSPIDER_MODULE = "zcspider.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "zcspider (+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 = {
+#    "zcspider.middlewares.ZcspiderSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "zcspider.middlewares.ZcspiderDownloaderMiddleware": 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 = {
+#    "zcspider.pipelines.ZcspiderPipeline": 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"
+
+ITEM_PIPELINES = {
+    'zcspider.pipelines.ZcspiderPipeline': 300,
+}

zcspider/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.

zcspider/spiders/base.py

@@ -0,0 +1,33 @@
+import scrapy
+from urllib.parse import urlparse
+import html2text
+
+class BaseSpider(scrapy.Spider):
+    name = "basespider"
+    start_urls = ["http://ctc.ac.cn/"]
+    visited_urls = set()
+
+    def  __init__(self, start_url: str, name=None, **kwargs):
+         super().__init__(name, **kwargs)
+         self.domain = urlparse(start_url).netloc
+         self.start_urls = [start_url]
+         self.ext = tuple(['.png', '.jpg', '.pdf', '.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx'])
+
+    def parse(self, response):
+        self.visited_urls.add(response.url)
+        h = html2text.HTML2Text()
+        h.ignore_links = True  # 忽略所有链接
+        # 提取纯文本内容
+        text = h.handle(response.body.decode())
+
+        yield {
+                'domain': self.domain,
+                'url': response.url,
+                'text': text,
+            }
+
+        for link in response.css("a::attr('href')").getall():
+            if link not in self.visited_urls:
+                    if link.startswith("/") or urlparse(link).netloc == self.domain:
+                        if not link.endswith(self.ext):
+                                yield scrapy.Request(response.urljoin(link), callback=self.parse)