init

config_spider/items.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class Item(scrapy.Item):
+    _id = scrapy.Field()
+    task_id = scrapy.Field()
+    ts = scrapy.Field()
+    job_list_title = scrapy.Field()
+    job_url = scrapy.Field()
+    com_name1 = scrapy.Field()
+    job_title = scrapy.Field()
+    job_num = scrapy.Field()
+    job_xueli = scrapy.Field()
+    job_yingjie = scrapy.Field()
+    job_des = scrapy.Field()
+    com_jiesao = scrapy.Field()
+    com_name2 = scrapy.Field()
+    job_xinzi = scrapy.Field()
+    com_url = scrapy.Field()
+    linkman = scrapy.Field()
+    linkemail = scrapy.Field()
+    site_link = scrapy.Field()
+    linktelpic = scrapy.Field()
+    com_name = scrapy.Field()
+    com_hangye = scrapy.Field()
+    com_guimo = scrapy.Field()
+    com_manguimo = scrapy.Field()
+    com_fuli = scrapy.Field()
+    com_teshe = scrapy.Field()
+    com_dec = scrapy.Field()
+    com_fanwei = scrapy.Field()
+    com_address = scrapy.Field()
+    com_add = scrapy.Field()
+

config_spider/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# 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
+
+
+class ConfigSpiderSpiderMiddleware(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 Request, 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 ConfigSpiderDownloaderMiddleware(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)

config_spider/pipelines.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# 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
+
+import os
+from pymongo import MongoClient
+
+mongo = MongoClient(
+    host=os.environ.get('CRAWLAB_MONGO_HOST') or 'localhost',
+    port=int(os.environ.get('CRAWLAB_MONGO_PORT') or 27017),
+    username=os.environ.get('CRAWLAB_MONGO_USERNAME'),
+    password=os.environ.get('CRAWLAB_MONGO_PASSWORD'),
+    authSource=os.environ.get('CRAWLAB_MONGO_AUTHSOURCE') or 'admin'
+)
+db = mongo[os.environ.get('CRAWLAB_MONGO_DB') or 'test']
+col = db[os.environ.get('CRAWLAB_COLLECTION') or 'test']
+task_id = os.environ.get('CRAWLAB_TASK_ID')
+
+class ConfigSpiderPipeline(object):
+    def process_item(self, item, spider):
+        item['task_id'] = task_id
+        if col is not None:
+            col.save(item)
+        return item

config_spider/settings.py

@@ -0,0 +1,111 @@
+# -*- coding: utf-8 -*-
+import os
+import re
+import json
+
+# Scrapy settings for config_spider 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 = 'Crawlab Configurable Spider'
+
+SPIDER_MODULES = ['config_spider.spiders']
+NEWSPIDER_MODULE = 'config_spider.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Crawlab Spider'
+
+# 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'config_spider.middlewares.ConfigSpiderSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'config_spider.middlewares.ConfigSpiderDownloaderMiddleware': 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 = {
+   'config_spider.pipelines.ConfigSpiderPipeline': 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'
+
+for setting_env_name in [x for x in os.environ.keys() if x.startswith('CRAWLAB_SETTING_')]:
+    setting_name = setting_env_name.replace('CRAWLAB_SETTING_', '')
+    setting_value = os.environ.get(setting_env_name)
+    if setting_value.lower() == 'true':
+        setting_value = True
+    elif setting_value.lower() == 'false':
+        setting_value = False
+    elif re.search(r'^\d+$', setting_value) is not None:
+        setting_value = int(setting_value)
+    elif re.search(r'^\{.*\}$', setting_value.strip()) is not None:
+        setting_value = json.loads(setting_value)
+    elif re.search(r'^\[.*\]$', setting_value.strip()) is not None:
+        setting_value = json.loads(setting_value)
+    else:
+        pass
+    locals()[setting_name] = setting_value
+

config_spider/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.

config_spider/spiders/spider.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+import scrapy
+import re
+from config_spider.items import Item
+from urllib.parse import urljoin, urlparse
+
+def get_real_url(response, url):
+    if re.search(r'^https?', url):
+        return url
+    elif re.search(r'^\/\/', url):
+        u = urlparse(response.url)
+        return u.scheme + url
+    return urljoin(response.url, url)
+
+class ConfigSpider(scrapy.Spider):
+    name = 'config_spider'
+
+    def start_requests(self):
+        yield scrapy.Request(url='https://linyi.58.com/renshizhuguan/pn3/?PGTID=0d302892-001f-99e7-35c5-0a69a314c4dd&ClickID=3', callback=self.parse_list)
+
+    def parse_list(self, response):
+        prev_item = response.meta.get('item')
+        for elem in response.css('li.job_item'):
+            item = Item()
+            item['job_list_title'] = elem.css('span.name::text').extract_first()
+            item['job_url'] = elem.css('div.job_name > a::attr("href")').extract_first()
+            item['com_name1'] = elem.css('div.comp_name > a::text').extract_first()
+            if prev_item is not None:
+                for key, value in prev_item.items():
+                    item[key] = value
+            yield scrapy.Request(url=get_real_url(response, item['job_url']), callback=self.parse_job_info, meta={'item': item})
+        next_url = response.css('a.next::attr("href")').extract_first()
+        yield scrapy.Request(url=get_real_url(response, next_url), callback=self.parse_list, meta={'item': prev_item})
+
+    def parse_job_info(self, response):
+        item = Item() if response.meta.get('item') is None else response.meta.get('item')
+        item['job_title'] = response.css('span.pos_name::text').extract_first()
+        item['job_num'] = response.css('span.pad_left_none::text').extract_first()
+        item['job_xueli'] = response.css('.pos_base_condition > span:nth-last-child(2)::text').extract_first()
+        item['job_yingjie'] = response.css('span.border_right_None::text').extract_first()
+        item['job_des'] = response.css('div.des *::text').extract_first()
+        item['com_jiesao'] = response.css('div.comp_intro *::text').extract_first()
+        item['com_name2'] = response.css('div.baseInfo_link > a::text').extract_first()
+        item['job_xinzi'] = response.css('span.pos_salary::text').extract_first()
+        item['com_url'] = response.css('div.baseInfo_link > a::attr("href")').extract_first()
+        yield scrapy.Request(url=get_real_url(response, item['com_url']), callback=self.parse_com_info, meta={'item': item})
+
+    def parse_com_info(self, response):
+        item = Item() if response.meta.get('item') is None else response.meta.get('item')
+        item['linkman'] = response.css('div.c_detail_item:nth-child(1) > em::text').extract_first()
+        item['linkemail'] = response.css('div.c_detail:nth-child(2) > div.c_detail_item:nth-child(2) > em::text').extract_first()
+        item['site_link'] = response.css('div.c_detail:nth-child(3) > div.c_detail_item:nth-child(2) > em::text').extract_first()
+        item['linktelpic'] = response.css('div.phone-protect > img::attr("src")').extract_first()
+        item['com_name'] = response.css('div.nan_title > h2::text').extract_first()
+        item['com_hangye'] = response.css('div.basic > p:nth-child(3) *::text').extract_first()
+        item['com_guimo'] = response.css('div.basic > p:nth-child(4) *::text').extract_first()
+        item['com_manguimo'] = response.css('div.basic > p:nth-child(5) *::text').extract_first()
+        item['com_fuli'] = response.css('div.welfare > div.w_label > span::text').extract_first()
+        item['com_teshe'] = response.css('div.feature > div.w_label > span::text').extract_first()
+        item['com_dec'] = response.css('div.introduction_box > p *::text').extract_first()
+        item['com_fanwei'] = response.css('div.buiness > div.b_detail > p:nth-child(8) *::text').extract_first()
+        item['com_address'] = response.css('div.buiness > div.b_detail > p:nth-child(9) *::text').extract_first()
+        item['com_add'] = response.css('p.a_address::text').extract_first()
+        yield item
+
+

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