mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-22 17:31:03 +01:00
updated Jenkinsfile
This commit is contained in:
Marvin Zhang
@@ -2,7 +2,6 @@
|
||||
### Features / Enhancement
|
||||
- **Documentation**: Better and much more detailed documentation.
|
||||
- **Better Crontab**: Make crontab expression through crontab UI.
|
||||
- **High Concurrency**: `gevent` + `flask` to support high concurrency. [#70](https://github.com/tikazyq/crawlab/issues/70)
|
||||
|
||||
### Bugs Fixes
|
||||
- **Deleting Spider**. Deleting a spider does not only remove record in db but also removing related folder, tasks and schedules. [#69](https://github.com/tikazyq/crawlab/issues/69)
|
||||
|
||||
2
Jenkinsfile
vendored
2
Jenkinsfile
vendored
@@ -37,7 +37,7 @@ pipeline {
|
||||
steps {
|
||||
echo 'Deploying....'
|
||||
sh """
|
||||
docker stop crawlab | true
|
||||
docker rm -f crawlab | true
|
||||
docker run -d --rm --name crawlab \
|
||||
-p 8080:8080 \
|
||||
-p 8000:8000 \
|
||||
|
||||
@@ -1,17 +0,0 @@
|
||||
# -*- 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()
|
||||
@@ -1,56 +0,0 @@
|
||||
# -*- 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)
|
||||
@@ -1,25 +0,0 @@
|
||||
# -*- 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 = os.environ['MONGO_HOST']
|
||||
MONGO_PORT = int(os.environ['MONGO_PORT'])
|
||||
MONGO_DB = os.environ['MONGO_DB']
|
||||
|
||||
|
||||
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
|
||||
@@ -1,89 +0,0 @@
|
||||
# -*- 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'
|
||||
@@ -1,4 +0,0 @@
|
||||
# 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.
|
||||
@@ -1,17 +0,0 @@
|
||||
# -*- 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(),
|
||||
)
|
||||
@@ -1,11 +0,0 @@
|
||||
# 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
|
||||
@@ -1,2 +0,0 @@
|
||||
from scrapy import cmdline
|
||||
cmdline.execute(["scrapy","crawl","juejin_spider"])
|
||||
Reference in New Issue
Block a user