Merge remote-tracking branch 'origin/dev'

Author: codists

.github/workflows/deploy.yml

@@ -0,0 +1,40 @@
+name: deploy
+
+on:
+  workflow_dispatch:
+
+  push:
+    branches: [ dev ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Deploy
+        uses: appleboy/ssh-action@v1.1.0
+        with:
+          host: ${{ secrets.REMOTE_HOST }}
+          port: ${{ secrets.REMOTE_PORT }}
+          username: ${{ secrets.REMOTE_USER }}
+          password: ${{ secrets.REMOTE_PASSWD }}
+          script: |
+              mkdir -p /www/code
+              cd /www/code
+              git clone https://github.com/codists/python-talk.git
+
+              mkdir -p /www/frontend/python_talk
+              cd /www/code/python-talk/frontend
+              npm install -y
+              npm run build
+              cp -r /www/code/python-talk/frontend/dist /www/frontend/python_talk/
+
+              cp -r /www/code/python-talk/deployment/common /www
+              cd /www/common/
+              docker compose -f docker-compose-common.yml up -d
+
+              mkdir -p /www/backend/python_talk
+              cp -r /www/code/python-talk/backend/ /www/backend/python_talk/
+              cd /www/backend/python_talk/backend
+              docker build -t python_talk:0.0.1 /www/backend/python_talk/backend
+              docker compose -f /www/backend/python_talk/backend/docker-compose.yml up -d

.github/workflows/workflow.yml

@@ -0,0 +1,4 @@
+name: workflow.yml
+on:
+
+jobs:

backend/booksbot/booksbot/__init__.py

@@ -0,0 +1,24 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+# class BooksbotItem(scrapy.Item):
+#     # define the fields for your item here like:
+#     # name = scrapy.Field()
+#     pass
+
+class BookItem(scrapy.Item):
+    # 书名
+    title = scrapy.Field()
+    # 作者
+    author = scrapy.Field()
+    # 出版日期
+    price = scrapy.Field()
+    # 描述
+    description = scrapy.Field()
+    # 书籍详情页
+    url = scrapy.Field()

backend/booksbot/booksbot/items.py

@@ -0,0 +1,100 @@
+# 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 ItemAdapter
+
+
+class BooksbotSpiderMiddleware:
+    # 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
+
+    async def process_start(self, start):
+        # Called with an async iterator over the spider start() method or the
+        # maching method of an earlier spider middleware.
+        async for item_or_request in start:
+            yield item_or_request
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class BooksbotDownloaderMiddleware:
+    # 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)

backend/booksbot/booksbot/middlewares.py

@@ -0,0 +1,31 @@
+# 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 BooksbotPipeline:
+#     def process_item(self, item, spider):
+#         return item
+from python_talk.models.book import Book
+from python_talk.extensions import db
+
+class BookPipeline:
+    def process_item(self, item, spider):
+        """
+        将采集到的数据存入数据库
+        """
+        print(item)
+        book = Book(**item)
+        db.session.add(book)
+        db.session.commit()
+
+    def open_spider(self, spider):
+        print('spider 打开')
+
+    def close_spider(self, spider):
+        print('spider 关闭')

backend/booksbot/booksbot/pipelines.py

@@ -0,0 +1,91 @@
+# Scrapy settings for booksbot 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 = "booksbot"
+
+SPIDER_MODULES = ["booksbot.spiders"]
+NEWSPIDER_MODULE = "booksbot.spiders"
+
+ADDONS = {}
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "booksbot (+http://www.yourdomain.com)"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Concurrency and throttling settings
+#CONCURRENT_REQUESTS = 16
+CONCURRENT_REQUESTS_PER_DOMAIN = 1
+DOWNLOAD_DELAY = 1
+
+# 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 = {
+#    "booksbot.middlewares.BooksbotSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "booksbot.middlewares.BooksbotDownloaderMiddleware": 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 = {
+#    "booksbot.pipelines.BooksbotPipeline": 300,
+# }
+ITEM_PIPELINES = {
+   "booksbot.pipelines.BookPipeline": 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
+# TWISTED_REACTOR = 'twisted.internet.selectreactor.SelectReactor'
+FEED_EXPORT_ENCODING = "utf-8"

backend/booksbot/booksbot/settings.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.