20241026

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

xueqiu/items.py

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class XueqiuItem(scrapy.Item):
+    # define the fields for your item here like:
+    _id = scrapy.Field()
+    task_id = scrapy.Field()
+    id = scrapy.Field()
+    text = scrapy.Field()
+    url = scrapy.Field()
+    target = scrapy.Field()
+    view_count = scrapy.Field()
+    mark = scrapy.Field()
+    created_at = scrapy.Field()
+    ts = scrapy.Field()
+    source = scrapy.Field()

xueqiu/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class XueqiuSpiderMiddleware(object):
+    # 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, dict 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 Response, dict
+        # 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 XueqiuDownloaderMiddleware(object):
+    # 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)

xueqiu/pipelines.py

@@ -0,0 +1,29 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import os
+
+from pymongo import MongoClient
+
+
+class XueqiuPipeline(object):
+    mongo = MongoClient(
+        host=os.environ.get('MONGO_HOST') or 'localhost',
+        port=int(os.environ.get('MONGO_PORT') or 27017)
+    )
+    db = mongo[os.environ.get('MONGO_DB') or 'crawlab_test']
+    col = db.get_collection(os.environ.get('CRAWLAB_COLLECTION') or 'results_xueqiu')
+
+    # create indexes
+    col.create_index('stocks')
+    col.create_index('id')
+    col.create_index('url')
+
+    def process_item(self, item, spider):
+        item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
+        if self.col.find_one({'id': item['id']}) is None:
+            self.col.save(item)
+            return item

xueqiu/settings.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for xueqiu project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'xueqiu'
+
+SPIDER_MODULES = ['xueqiu.spiders']
+NEWSPIDER_MODULE = 'xueqiu.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
+
+# 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    'xueqiu.middlewares.XueqiuSpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'xueqiu.middlewares.XueqiuDownloaderMiddleware': 543,
+# }
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+# EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+# }
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'xueqiu.pipelines.XueqiuPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://doc.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://doc.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'

xueqiu/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.

xueqiu/spiders/xueqiu_spider.py

@@ -0,0 +1,46 @@
+# -*- coding: utf-8 -*-
+import json
+from datetime import datetime
+from time import sleep
+
+import scrapy
+
+from xueqiu.items import XueqiuItem
+
+
+class XueqiuSpiderSpider(scrapy.Spider):
+    name = 'xueqiu_spider'
+    allowed_domains = ['xueqiu.com']
+
+    def start_requests(self):
+        return [scrapy.Request(
+            url='https://xueqiu.com',
+            callback=self.parse_home
+        )]
+
+    def parse_home(self, response):
+        yield scrapy.Request(
+            url='https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=-1&count=20&category=6'
+        )
+
+    def parse(self, response):
+        data = json.loads(response.body)
+        next_max_id = data.get('next_max_id')
+        sleep(1)
+        for row in data.get('list'):
+            d = json.loads(row.get('data'))
+            item = XueqiuItem(
+                id=d['id'],
+                text=d['text'],
+                mark=d['mark'],
+                url=d['target'],
+                created_at=d['created_at'],
+                ts=datetime.fromtimestamp(d['created_at'] / 1e3),
+                view_count=d['view_count'],
+                source='xueqiu'
+            )
+            yield item
+
+        yield scrapy.Request(
+            url=f'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id={next_max_id}&count=20&category=6'
+        )