Added spider for Naukri.com #1 Fixed

Author: ravishhankar

joble/__init__.py

@@ -0,0 +1,14 @@
+# -*- 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 JobleItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

joble/items.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 JobleSpiderMiddleware:
+    # 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 JobleDownloaderMiddleware:
+    # 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)

joble/middlewares.py

@@ -0,0 +1,11 @@
+# -*- 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
+
+
+class JoblePipeline:
+    def process_item(self, item, spider):
+        return item

joble/pipelines.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for joble 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 = 'joble'
+
+SPIDER_MODULES = ['joble.spiders']
+NEWSPIDER_MODULE = 'joble.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'joble (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'joble.middlewares.JobleSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'joble.middlewares.JobleDownloaderMiddleware': 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 = {
+#    'joble.pipelines.JoblePipeline': 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'

joble/settings.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.

joble/spiders/__init__.py

@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+import scrapy
+import urllib
+
+
+class NaukriSpider(scrapy.Spider):
+    name = 'naukri'
+    allowed_domains = ['naukri.com']
+    start_urls = ['https://www.naukri.com']
+
+    def __init__(self, keyword=None, count=20, city=None):
+        self.count = count
+        self.keyword = keyword
+        self.city = city
+
+    def get_url(self):
+        base_url = 'https://www.naukri.com/jobapi/v3/search?'
+        params = {
+            'noOfResults': self.count,
+            'urlType': 'search_by_key_loc',
+            'searchType': 'adv',
+            'keyword': self.keyword,
+            'location': self.city,
+            'sort': 'r',
+            'k': self.keyword,
+            'l': self.city,
+            'seoKey': '{}-jobs-in-{}'.format(self.keyword, self.city) if self.city else '{}-jobs'.format(self.keyword),
+            'src': 'jobsearchDesk',
+            'latLong': ''
+        }
+        default = ['keyword', 'sort', 'l', 'k', 'location']
+        if self.city is None:
+            for key in default:
+                params.pop(key)
+        return {
+            'url': base_url,
+            'body': params
+        }
+
+    def parse(self, response):
+        if self.keyword:
+            record = self.get_url()
+            yield scrapy.Request(url=record['url']+urllib.parse.urlencode(record['body']),
+                headers={'User-Agent': "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:74.0) Gecko/20100101 Firefox/74.0", 'appid': '109', 'systemid': '109'},
+                meta={'keyword': self.keyword},
+                callback=self.jobData)
+        else:
+            yield scrapy.Request('https://www.naukri.com/jobs-by-category',
+                callback=self.get_by_category)
+
+    def get_by_category(self, response):
+        for j in response.xpath('//div[@class="lmrWrap wrap"]/div/div/div/a'):
+            title = j.xpath('text()').get().strip()
+            url = j.xpath('@href').get().strip()
+            yield scrapy.Request(url,
+                callback=self.job_list,
+                meta={'keyword': title, 'count': 0, 'plink': url})
+
+    def job_list(self, response):
+        plink = response.meta['plink'].split('/')[-1]
+        keyword = plink.split('-jobs')[0]
+        seokeys = keyword+'-jobs'
+        ids = plink.split('=')[-1]
+        joburl = 'https://www.naukri.com/jobapi/v3/search?noOfResults=20&urlType=search_by_keyword&searchType=adv&keyword={}&xt=catsrch&functionAreaId={}&seoKey={}&src=jobsearchDesk&latLong='.format(keyword, ids, seokeys)
+        yield scrapy.Request(joburl,
+            headers={'Referer': response.meta['plink'],
+                'User-Agent': "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:74.0) Gecko/20100101 Firefox/74.0",
+                'appid': '109',
+                'systemid':  '109'},
+            meta={'url': response.meta['plink'], 'keyword': keyword, 'ids': ids, 'seokeys': seokeys},
+            callback=self.jobData)
+
+    def jobData(self, response):
+        data = response.text
+        data = data.replace('false', 'False')
+        data = data.replace('true', 'True')
+        jobdata = eval(data)
+        if jobdata.get('jobDetails'):
+          for job in jobdata['jobDetails']:
+            place = job['placeholders']
+            detail = {}
+            for p in place:
+                key, value = p.values()
+                detail[key] = value
+            details = {
+                'category': response.meta['keyword'],
+                'title': job['title'],
+                'jobId': job['jobId'],
+                'companyName': job['companyName'],
+                'skills': job.get('tagsAndSkills'),
+                'joburl': job['jdURL'],
+                'postedon': job['footerPlaceholderLabel'],
+                'descreption': job.get('jobDescription')
+            }
+            final_result = {**detail, **details}
+            yield final_result

joble/spiders/naukri.py

@@ -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 = joble.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = joble