init

.gitignore

@@ -0,0 +1 @@
+__pycache__

linyidzwww/items.py

@@ -0,0 +1,38 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+from scrapy.loader.processors import MapCompose, TakeFirst
+
+#移除空格
+def remove_spaces(text):
+    return text.replace(" ", "")
+# 使用replace方法移除换行符、制表符、换行符、
+def remove_special_chars(text):
+    cleaned_text = text.replace("\n", "").replace("\t", "").replace("\r", "").replace("\f", "").replace("\v", "")
+    return cleaned_text
+# 处理 \uXXXX格式的unicode字符
+def replace_unicode(text):
+    cleaned_text = text.replace("<!--zhengwen-->", "").replace("<!--/zhengwen-->", "").replace("news-con", "news-content")
+    cleaned_text = cleaned_text.replace("<p style=\"text-align: center;\"><strong>海报新闻出品</strong></p>", "")
+    cleaned_text = cleaned_text.replace("<p style=\"text-align: center;\">海报新闻出品</p>", "")
+    cleaned_text = cleaned_text.replace("海报新闻出品", "")
+    #cleaned_text = cleaned_text.encode('utf-8').decode('unicode_escape')
+    print(cleaned_text)
+    return cleaned_text
+def remove_content_chars(text):
+    cleaned_text = text.replace('<!--zhengwen-->', "").replace('<!--/zhengwen-->', "").replace("news-con", "news-content")
+    cleaned_text = cleaned_text.replace("<p style=\"text-align: center;\"><strong>海报新闻出品</strong></p>", "")
+    cleaned_text = cleaned_text.replace("<p style=\"text-align: center;\">海报新闻出品</p>", "")
+    cleaned_text = cleaned_text.replace("海报新闻出品", "")
+    return cleaned_text
+class LinyidzwwwItem(scrapy.Item):
+    title = scrapy.Field()#标题
+    url = scrapy.Field()#链接
+    datetime = scrapy.Field()#日期时间
+    content = scrapy.Field(output_processor = MapCompose(remove_spaces,remove_special_chars,replace_unicode))#内容
+    thumb = scrapy.Field()#封面图片
+    source = scrapy.Field()#来源
+    author = scrapy.Field()#作者

linyidzwww/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 LinyidzwwwSpiderMiddleware:
+    # 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 LinyidzwwwDownloaderMiddleware:
+    # 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)

linyidzwww/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 LinyidzwwwPipeline:
+    def process_item(self, item, spider):
+        return item

linyidzwww/settings.py

@@ -0,0 +1,102 @@
+# Scrapy settings for linyidzwww 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 = "linyidzwww"
+
+SPIDER_MODULES = ["linyidzwww.spiders"]
+NEWSPIDER_MODULE = "linyidzwww.spiders"
+
+# 使用scrapy-redis里的去重组件，不使用scrapy默认的去重方式
+#一个去重的类，用来将url去重
+DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
+#一个队列
+SCHEDULER = "scrapy_redis.scheduler.Scheduler"
+#是否持久化（爬完后不会再爬了，像一些固定的数据）
+SCHEDULER_PERSIST = True
+#你的redis地址
+REDIS_URL = "redis://default:jhkdjhkjdhsIUTYURTU_hFBi3n@192.168.192.217:6379"
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1 Edg/120.0.0.0"
+
+# 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,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+   "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
+   "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1 Edg/120.0.0.0"
+}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    "linyidzwww.middlewares.LinyidzwwwSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "linyidzwww.middlewares.LinyidzwwwDownloaderMiddleware": 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 = {
+   "linyidzwww.pipelines.LinyidzwwwPipeline": 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"

linyidzwww/spiders/LinyiNews.py

@@ -0,0 +1,63 @@
+import scrapy
+import re
+from linyidzwww.items import LinyidzwwwItem,replace_unicode
+from scrapy.loader import ItemLoader
+
+class LinyiNewsSpider(scrapy.Spider):
+    name = "linyinews"
+    allowed_domains = ["linyi.dzwww.com"]
+    start_urls = ["https://linyi.dzwww.com/news/index.htm"]
+    # for num in range(1,29):
+    #     start_urls.append("https://linyi.dzwww.com/news/index_"+str(num)+".htm")
+    def parse(self, response):
+        for sel in response.css('div.tuwen>ul>li'):
+            title = sel.css('h3>a::text').extract()[0]
+            url = sel.css('h3>a::attr(href)').extract()[0]
+            thumb = sel.css('i>a>img::attr(src)').extract()[0]
+            if not thumb:
+                thumb = ''
+            source = sel.css('div.tail>span.left::text').extract()[1].strip()
+            yield scrapy.Request(url, callback=self.parse_article, meta={'title': title, 'url': url, 'thumb': thumb,'source':source})
+    def parse_article(self, response):
+        title = response.meta['title']
+        url = response.meta['url']
+        thumb = response.meta['thumb']
+        source = response.meta['source']
+        if not title:
+            title = response.css('div.layout>h2::text').extract()[0]
+        info = response.css('div.layout>div.left::text').extract()[0]
+        # 匹配并提取时间
+        time_pattern = r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})'
+        match_time = re.search(time_pattern, info)
+        if match_time:
+            datetime = match_time.group(1).strip()
+        else:
+            datetime = ''
+        if not source:
+            # 匹配并提取来源
+            source_pattern = r'来源: (.*)　作者:'
+            match_source = re.search(source_pattern, info)
+            if match_source:
+                source = match_source.group(1).strip()
+            else:
+                source = ''
+        # 匹配并提取作者
+        author_pattern = r'作者: (.*)'
+        match_author = re.search(author_pattern, info)
+        if match_author:
+            author = match_author.group(1).strip()
+        else:
+            author = ''
+        # 匹配并提取内容
+        html_content  = response.css('div.news-con')[0].get().replace("\n", "").strip()
+        # content = re.sub(r'<video.*?</video>', '', html_content, flags=re.DOTALL)
+        # 数据处理器
+        item = LinyidzwwwItem()
+        item['title'] = title
+        item['url'] = url
+        item['thumb'] = thumb
+        item['source'] = source
+        item['datetime'] = datetime
+        item['author'] = author
+        item['content'] = replace_unicode(html_content)
+        yield item

linyidzwww/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.

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