Merge pull request #14 from muzico425/develop

change print to logger

crawlab/app.py

@@ -8,7 +8,7 @@ from celery import Celery
 from flask import Flask
 from flask_cors import CORS
 from flask_restful import Api
-
+from utils.log import other
 from constants.node import NodeStatus
 from db.manager import db_manager
 from routes.schedules import ScheduleApi
@@ -78,7 +78,7 @@ def monitor_nodes_status(celery_app):
         })
 
     def update_nodes_status_online(event):
-        print(event)
+        other.info(f"{event}")
 
     with celery_app.connection() as connection:
         recv = celery_app.events.Receiver(connection, handlers={

crawlab/bin/run_flower.py

@@ -6,11 +6,11 @@ import subprocess
 file_dir = os.path.dirname(os.path.realpath(__file__))
 root_path = os.path.abspath(os.path.join(file_dir, '..'))
 sys.path.append(root_path)
-
+from utils.log import other
 from config import BROKER_URL
 
 if __name__ == '__main__':
     p = subprocess.Popen(['celery', 'flower', '-b', BROKER_URL], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
     for line in iter(p.stdout.readline, 'b'):
         if line.decode('utf-8') != '':
-            print(line.decode('utf-8'))
+            other.info(line.decode('utf-8'))

crawlab/config.py

@@ -1,7 +1,8 @@
 # project variables
 # 爬虫源码路径
 PROJECT_SOURCE_FILE_FOLDER = '../spiders'
-
+# 配置python虚拟环境的路径
+PYTHON_ENV_PATH="/Users/chennan/Desktop/2019/env/bin/python"
 # 爬虫部署路径
 PROJECT_DEPLOY_FILE_FOLDER = '../deployfile'
 
@@ -29,4 +30,5 @@ MONGO_DB = 'crawlab_test'
 # flask variables
 DEBUG = True
 FLASK_HOST = '127.0.0.1'
-FLASK_PORT = 8000
+FLASK_PORT = 8000
+

crawlab/manage.py

@@ -24,7 +24,7 @@ from routes.spiders import SpiderApi, SpiderImportApi, SpiderManageApi
 from routes.stats import StatsApi
 from routes.tasks import TaskApi
 from tasks.celery import celery_app
-
+from utils.log import other
 # flask app instance
 app = Flask(__name__)
 app.config.from_object('config')
@@ -81,7 +81,7 @@ def run_flower():
     p = subprocess.Popen(['celery', 'flower', '-b', BROKER_URL], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
     for line in iter(p.stdout.readline, 'b'):
         if line.decode('utf-8') != '':
-            print(line.decode('utf-8'))
+            other.info(line.decode('utf-8'))
 
 
 def run_worker():

crawlab/tasks/spider.py

@@ -2,15 +2,12 @@ import os
 from datetime import datetime
 
 from bson import ObjectId
-from celery.utils.log import get_logger
-
-from config import PROJECT_DEPLOY_FILE_FOLDER, PROJECT_LOGS_FOLDER
+from config import PROJECT_DEPLOY_FILE_FOLDER, PROJECT_LOGS_FOLDER,PYTHON_ENV_PATH
 from constants.task import TaskStatus
 from db.manager import db_manager
 from .celery import celery_app
 import subprocess
-
-logger = get_logger(__name__)
+from utils.log import other as logger
 
 
 @celery_app.task(bind=True)
@@ -19,6 +16,8 @@ def execute_spider(self, id: str):
     hostname = self.request.hostname
     spider = db_manager.get('spiders', id=id)
     command = spider.get('cmd')
+    if command.startswith("env"):
+        command = PYTHON_ENV_PATH + command.replace("env","")
 
     current_working_directory = os.path.join(PROJECT_DEPLOY_FILE_FOLDER, str(spider.get('_id')))
 

crawlab/utils/deploy.py

@@ -1,5 +1,5 @@
 import os, zipfile
-
+from utils.log import other
 
 # 打包目录为zip文件（未压缩）
 def zip_file(source_dir, output_filename):
@@ -20,4 +20,4 @@ def unzip_file(zip_src, dst_dir):
         for file in fz.namelist():
             fz.extract(file, dst_dir)
     else:
-        print('This is not zip')
+        other.info('This is not zip')

crawlab/utils/spider.py

@@ -3,7 +3,6 @@ import os
 from constants.spider import FILE_SUFFIX_LANG_MAPPING, LangType, SUFFIX_IGNORE, SpiderType
 from db.manager import db_manager
 
-
 def get_lang_by_stats(stats: dict) -> LangType:
     """
     :param stats: stats is generated by utils.file.get_file_suffix_stats
@@ -18,7 +17,7 @@ def get_lang_by_stats(stats: dict) -> LangType:
             return FILE_SUFFIX_LANG_MAPPING.get(top_suffix)
         return LangType.OTHER
     except IndexError as e:
-        print(e.args,stats)
+        pass
 
 
 

deployfile/5ca46b508ffaed82c65f0f9c/juejin/items.py

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class JuejinItem(scrapy.Item):
+    # define the fields for your item here like:
+    _id = scrapy.Field()
+    title = scrapy.Field()
+    link = scrapy.Field()
+    like = scrapy.Field()
+    task_id = scrapy.Field()

deployfile/5ca46b508ffaed82c65f0f9c/juejin/middlewares.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class JuejinSpiderMiddleware(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)

deployfile/5ca46b508ffaed82c65f0f9c/juejin/pipelines.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import os
+
+from pymongo import MongoClient
+
+MONGO_HOST = '127.0.0.1'
+MONGO_PORT = 27017
+MONGO_DB = 'crawlab_test'
+
+
+class JuejinPipeline(object):
+    mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT)
+    db = mongo[MONGO_DB]
+    col_name = os.environ.get('CRAWLAB_COLLECTION','test')
+    col = db[col_name]
+
+    def process_item(self, item, spider):
+        item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
+        self.col.save(item)
+        return item

deployfile/5ca46b508ffaed82c65f0f9c/juejin/settings.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for juejin project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'juejin'
+
+SPIDER_MODULES = ['juejin.spiders']
+NEWSPIDER_MODULE = 'juejin.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/67.0.3396.99 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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    'juejin.middlewares.JuejinSpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'juejin.middlewares.MyCustomDownloaderMiddleware': 543,
+# }
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+# EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+# }
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'juejin.pipelines.JuejinPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://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 http://scrapy.readthedocs.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'

deployfile/5ca46b508ffaed82c65f0f9c/juejin/spiders/__init__ 2.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.

deployfile/5ca46b508ffaed82c65f0f9c/juejin/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.

deployfile/5ca46b508ffaed82c65f0f9c/juejin/spiders/juejin_spider.py

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from juejin.items import JuejinItem
+
+
+class JuejinSpiderSpider(scrapy.Spider):
+    name = 'juejin_spider'
+    allowed_domains = ['juejin.com']
+    start_urls = ['https://juejin.im/search?query=celery']
+
+    def parse(self, response):
+        for item in response.css('ul.main-list > li.item'):
+            yield JuejinItem(
+                title=item.css('.title span').extract_first(),
+                link=item.css('a::attr("href")').extract_first(),
+                like=item.css('.like .count::text').extract_first(),
+            )

deployfile/5ca46b508ffaed82c65f0f9c/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = juejin.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = juejin

deployfile/5ca46b508ffaed82c65f0f9c/start.py

@@ -0,0 +1,2 @@
+from scrapy import cmdline
+cmdline.execute(["scrapy","crawl","juejin_spider"])

deployfile/5ca46b508ffaed82c65f0fa0/juejin_spider 2.js

@@ -52,7 +52,7 @@ const MongoClient = require('mongodb').MongoClient;
   });
 
   // open database connection
-  const client = await MongoClient.connect('mongodb://192.168.99.100:27017');
+  const client = await MongoClient.connect('mongodb://127.0.0.1:27017');
   let db = await client.db('crawlab_test');
   const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin';
   const taskId = process.env.CRAWLAB_TASK_ID;