fix

Backflows/runner.py

@@ -66,7 +66,6 @@ def is_project_context():
     # print('spider_dir:', spider_dir)
 else:
     print('settings.py 未找到，无法确定项目上下文')
-
 # If in a project context, add the current directory to sys.path
 if is_project_context():
     sys.path.insert(0, os.getcwd())
@@ -76,7 +75,7 @@ def is_project_context():
         from downloadMiddleware import UserAgentMiddleware, RetryMiddleware, ProxyMiddleware
         from pipeline import Pipeline
 
-        logger.info("Running in project context.")
+        # logger.info("Running in project context.")
     except ImportError as e:
         logger.error(f"Error importing project modules: {e}")
         sys.exit(1)  # Exit if essential project modules are missing

backflow_core/downloadMiddleware.py

@@ -5,7 +5,7 @@
 
 import random
 from loguru import logger
-from . import settings
+import settings
 from Backflows.middleware import DownloadMiddleware
 
 

backflow_core/pipeline.py

@@ -7,7 +7,7 @@
 import json
 import pymongo
 import asyncio
-from .settings import MONGO_URI, MONGO_DATABASE, DATA_FILE_PATH
+from settings import MONGO_URI, MONGO_DATABASE, DATA_FILE_PATH
 
 
 class Pipeline:

backflow_core/spiders/__init__.py

@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+# @Author  : ysl
+# @File    : __init__.py.py

backflow_core/spiders/dongfangcaifu.py

@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+# @Author  : ysl
+# @File    : dongfangcaifu.py.py
+
+from loguru import logger
+from utils.tools import Tools
+from Backflows.base import BackFlow
+from Backflows.middleware import Request
+from parsel import Selector
+import traceback
+
+
+class Dongfangcaifu(BackFlow):
+    name = 'dongfangcaifu'
+
+    def __init__(self):
+        super().__init__()
+        self.ck = None
+        self.headers = {
+            'Cookie': 'st_si=07577822841164; st_asi=delete; qgqp_b_id=29bf1bcc2d53a8587adedc785cc087ba; st_pvi=23828108194402; st_sp=2024-12-03%2014%3A12%3A08; st_inirUrl=https%3A%2F%2Fwww.google.com%2F; st_sn=162; st_psi=20250106105653308-113104302701-4707866973',
+            'Referer': 'https://finance.eastmoney.com/a/ccjdd_2.html',
+            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+        }
+
+    async def get_page_request(self, page):
+        url = 'https://finance.eastmoney.com/a/ccjdd_{}.html'.format(page)
+        yield Request('GET', url=url, headers=self.headers, cookies=self.ck, meta={'page': page})
+
+    async def parse(self, response):
+        resp = response.text
+        resp = Selector(resp)
+        nodes = resp.xpath("//div[@class='artitleList']//li//a")
+        for node in nodes:
+            title = node.xpath("./text()").get()
+            url = node.xpath("./@href").get()
+            news = {
+                'url': url,
+                'title': title,
+            }
+            yield news

setup.py

@@ -28,7 +28,7 @@ def run(self):
 
 setup(
     name='backflow',
-    version='0.2.2',  # Increment the version
+    version='0.2.3',  # Increment the version
     author='ysl',  # 替换为你的名字
     author_email='[email protected]',  # 替换为你的邮箱
     description='A simple crawler framework that implements both single run and distributed run based on Celery,'