def parse(self, response):
job = Job()
job["website"] = self.meta["name"]
job["url"] = response.url
job["readvertised"] = "N/A"
job["year"] = "2020"
job["positionLevel"] = "N/A"
job["positions"] = 1
job["jobTitle"] = response.xpath(
'//div[@class="flex-full"]/h3[contains(@class, "mt-500")]/text()'
).get()
location = response.xpath(
'//div[contains(@class, "mb-500")]/text()').get()
if location is not None:
job["country"] = location.split(',')[-1].strip()
job["town"] = location.split(',')[0].strip()
job["company"] = response.xpath(
'//div[contains(@class, "mb-500")]/a/text()').get()
job["salary"] = response.xpath(
'//div[@class="flex-full"]/p[1]/span[contains(text(), "Salary")]/following::span/text()'
).get()
employmentType = response.xpath(
'//div[@class="flex-full"]/p[1]/text()').getall()
if len(employmentType) > 0:
job["employmentType"] = employmentType[1].strip()
job["jobType"] = employmentType[1].strip()
divs = response.css('div.row-flex div.border-grey-sm *::text').getall()
titles = response.xpath(
'//h4/text() | //strong /text() | //b/text()').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = self.clean_text(
response.css('header h1::text').get())
job["positionLevel"] = "N/A"
job["positions"] = 1
job["readvertised"] = "N/A"
job["year"] = "2020"
job["company"] = self.clean_text(response.css('p.company::text').get())
job["technology"] = self.clean_text(
response.css('header h1::text').get())
job["industry"] = self.clean_text(
response.css('header h1::text').get())
job["country"] = "Kenya"
self.get_header_details(
response.css('header .details li *::text').getall(), job)
self.get_tagged_details(
response.css('header .tags li span::text').getall(), job)
divs = response.css('.content *::text').getall()
titles = response.xpath(
'//h3/text() | //strong /text() | //b/text()').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["domain"]
job["url"] = response.url
job["jobTitle"] = response.css('selector::text').get()
job["jobType"] = response.css('selector::text').get()
job["positionLevel"] = response.css('selector::text').get()
job["positions"] = response.css('selector::text').get()
job["uploadDate"] = response.css('selector::text').get()
job["year"] = response.css('selector::text').get()
job["deadline"] = response.css('selector::text').get()
job["town"] = response.css('selector::text').get()
job["contact"] = response.css('selector::text').get()
job["readvertised"] = response.css('selector::text').get()
job["salary"] = response.css('selector::text').get()
job["company"] = response.css('selector::text').get()
job["technology"] = response.css('selector::text').get()
job["description"] = response.css('selector::text').get()
job["employmentType"] = response.css('selector::text').get()
job["skills"] = response.css('selector::text').get()
job["industry"] = response.css('selector::text').get()
job["responsibilities"] = response.css('selector::text').get()
job["requirements"] = response.css('selector::text').get()
job["country"] = "Kenya"
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('#postJob h2::text').get()
job["positions"] = 1
job["uploadDate"] = response.xpath(
"//span[contains(text(), 'Posted')]/*/text()").get()
job["year"] = "2020"
job["deadline"] = "N/A"
job["town"] = self.clean_text(' '.join(
response.css('div.card-body div.pb-3 p::text').getall()))
job["readvertised"] = "N/A"
job["salary"] = "Login to view salary"
job["country"] = "Kenya"
self.get_header_details(
response.css(
'#job-description div.card-body div.pb-3 a *::text').getall(),
job)
divs = response.css('#job-description div.card-body *::text').getall()
titles = response.xpath(
'//h5/text() | //strong /text() | //b/text()').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["positionLevel"] = "N/A"
job["positions"] = 1
job["readvertised"] = "N/A"
job["country"] = "Kenya"
titles = response.xpath(
'//h1 /text() | //h2 /text() | //h3 /text() | //h4 /text() | //strong /text() | //b/text()'
).getall()
divs = response.css('body *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('h1.h2::text').get()
job["company"] = response.xpath(
"//h1[@class='h2']/following-sibling::h4/text()")
job["positions"] = 1
job["readvertised"] = "N/A"
job["country"] = "Kenya"
titles = response.xpath(
'//h1 /text() | //h4 /text() | //strong /text() | //b/text()'
).getall()
divs = response.css('div.container *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"]= self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('article.post h2 a::text').get()
job["jobType"] = "N/A"
job["positions"] = 1
job["uploadDate"] = response.css('div#meta_authorl::text').get()
job["readvertised"] = "N/A"
job["company"] = response.css('article.post h2 a::text').get().split(" at ")[-1]
job["employmentType"] = "N/A"
job["country"] = "Kenya"
titles = response.xpath('//h3/text() | //strong /text() | //b/text()').getall()
divs = response.css('article.post *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"]= 1
job["website"] = self.meta["name"]
job["url"] = response.url
title = self.clean_text(response.css('.b-advert-title-inner::text').get())
job["jobTitle"] = title
job["positions"] = 1
job["description"] = title
job["technology"] = title
job["uploadDate"] = self.clean_text(response.css('time::text').get())
job["town"] = self.clean_text(response.css('.b-advert-info-statistics::text').get())
job["year"] = "2020"
job["contact"] = "N/A"
job["readvertised"] = "N/A"
job["country"] = "Kenya"
divs = response.css(".b-advert-attributes *::text").getall()
self.get_details(divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"]= self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('header h1.title::text').get()
job["positionLevel"] = response.css('header h1.title::text').get()
job["positions"] = 1
job["uploadDate"] = response.css('time.time::attr(datetime)').get()
job["deadline"] = response.css('selector::text').get()
job["readvertised"] = "N/A"
job["salary"] = "N/A"
job["technology"] = response.css('header h1.title::text').get()
job["country"] = "Kenya"
self.get_header_details(response.css('article header span::text').getall(), job)
titles = response.xpath('//h3/text() | //strong /text() | //b/text()').getall()
divs = response.css('.content *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('h1.entry-title::text').get().split(
"–")[0]
job["jobType"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Job Type:']/span[@class='job-meta-content']/text()"
).get()
job["positionLevel"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Career Level:']/span[@class='job-meta-content']/text()"
).get()
job["positions"] = 1
job["uploadDate"] = "N/A"
job["year"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Deadline:']/span[@class='job-meta-content']/text()"
).get().strip().split(" ")[-1]
job["deadline"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Deadline:']/span[@class='job-meta-content']/text()"
).get()
job["town"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Location:']/span[@class='job-meta-content']/text()"
).get()
job["readvertised"] = "N/A"
job["company"] = "N/A"
job["technology"] = response.css('h1.entry-title::text').get().split(
"–")[0]
job["employmentType"] = response.xpath(
"//div[@class='single-job-meta']/ul/li[span[@class='job-meta-title']/text() = 'Job Type:']/span[@class='job-meta-content']/text()"
).get()
job["industry"] = response.css('h1.entry-title::text').get()
job["country"] = "Kenya"
titles = response.xpath('//strong /text() | //b/text()').getall()
divs = response.css('div.entry-content *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = self.clean_text(
response.css('.job-header__title::text').get())
job["positions"] = 1
jobType = self.clean_text(
response.css('.job-header__work-type::text').get())
job["jobType"] = jobType
job["employmentType"] = jobType
job["year"] = "2020"
job["readvertised"] = "N/A"
job["salary"] = self.clean_text(
response.css('.job-header__salary::text').get())
job["country"] = "Kenya"
self.get_town(
response.css('.job-header__location *::text').getall(), job)
self.get_company(response.css('h2 *::text').getall(), job)
self.get_description(
response.css('.job__details *::text').getall(), job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
jobTitle = self.clean_text(response.css('h1::text').get())
job["jobTitle"] = jobTitle
job["technology"] = jobTitle
job["industry"] = jobTitle
job["positionLevel"] = "N/A"
job["year"] = "2020"
job["readvertised"] = "N/A"
job["company"] = self.clean_text(response.css('h2::text').get())
job["skills"] = response.css('selector::text').get()
job["responsibilities"] = "N/A"
job["country"] = "Kenya"
self.get_type(response.css('.box_r *::text').getall(), job)
self.get_header_details(
response.css('header span::text').getall(), job)
self.get_description(
response.css('.detalle_oferta ul *::text').getall(), job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"]= self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.css('a.subjob-title::text').get()
job["jobType"] = response.xpath("//ul[@class='job-key-info']/li[span[@class='jkey-title']/text() = 'Job Type']/span[@class='jkey-info']/a/text()").get()
job["positionLevel"] = "N/A"
job["positions"] = 1
job["uploadDate"] = response.css('div#posted-date::text').get()
job["year"] = response.css('div#posted-date::text').get().strip().split(",")[-1]
job["deadline"] = response.css('div.read-date-sec-li:nth-child(2)::text').get()
job["town"] = response.xpath("//ul[@class='job-key-info']/li[span[@class='jkey-title']/text() = 'Location']/span[@class='jkey-info']/a/text()").get()
job["readvertised"] = "N/A"
job["company"] = response.css('li.job-industry a::text').get()
job["technology"] = response.xpath("//ul[@class='job-key-info']/li[span[@class='jkey-title']/text() = 'Job Field']/span[@class='jkey-info']/a/text()").get()
job["employmentType"] = response.xpath("//ul[@class='job-key-info']/li[span[@class='jkey-title']/text() = 'Job Type']/span[@class='jkey-info']/a/text()").get()
job["industry"] = response.css('li.job-industry a::text').get()
job["country"] = "Kenya"
titles = response.xpath('//strong /text() | //b/text()').getall()
divs = response.css('#job-description-holder *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
job["ID"] = 1
job["website"]= self.meta["name"]
job["url"] = response.url
job["jobTitle"] = response.xpath('//h1[@class="entry-title"]/text()').get()
job["jobType"] = response.xpath('//span[@itemprop="employmentType"]/text()').get()
job["positionLevel"] = response.xpath('//h1[@class="entry-title"]/text()').get()
job["positions"] = 1
job["uploadDate"] = response.xpath('//span[@class="updated"]/text()').get()
job["year"] = response.xpath('//span[@class="updated"]/text()').get().split(',')[-1].strip()
job["deadline"] = "N/A"
job["town"] = response.xpath('//span[@itemprop="address"]/text()').get()
job["reavertised"] = "N/A"
job["company"] = response.css('.wpjb-job-company::text').get()
job["technology"] = response.xpath('//span[@itemprop="occupationalCategory"]/text()').get()
job["employmentType"] = response.xpath('//span[@itemprop="employmentType"]/text()').get()
job["industry"] = response.xpath('//span[@itemprop="occupationalCategory"]/text()').get()
job["country"] = "Kenya"
titles = response.xpath('//h3/text() | //strong /text() | //b/text()').getall()
divs = response.css('.wpjb-job-content *::text').getall()
self.get_description(titles, divs, job)
return job
def parse(self, response):
job = Job()
jobContent = response.xpath(
'//main[@class="content"]/article[contains(@class, "job_posting")]'
)
jobDetails = jobContent.xpath('//div[@class="entry-content"]')
jobMeta = response.xpath('//footer/p[@class="entry-meta"]')
title = jobContent.xpath(
'//header[@class="entry-header"]/h1[@class="entry-title"]/text()'
).get()
uploadTime = jobContent.xpath(
'//header[@class="entry-header"]/p/time/text()').get()
if uploadTime:
year = uploadTime.split(" ")[2]
else:
year = "N/A"
jobType = jobMeta.xpath(
'//span[contains(@class, "wsm-categories")]/a[1]/text()').get()
description = ''.join(
jobDetails.xpath(
'//p/strong[contains(text(), "Title")]/ancestor::p/preceding-sibling::p/text()'
).getall())
salary = jobDetails.xpath(
'//p/strong[contains(text(), "Gross Salary")]/ancestor::p/text()'
).get()
if salary:
salary = salary.strip()
else:
salary = "N/A"
town = jobDetails.xpath(
'//p/strong[contains(text(), "Location")]/ancestor::p/text()').get(
)
if town is not None:
town = town.strip()
else:
town = "N/A"
skills = ''.join(
jobDetails.xpath(
'//p/span/strong[contains(text(), "Qualifications")]/ancestor::p/following-sibling::ul[1]/li/text()'
).getall())
responsibilities = ''.join(
jobDetails.xpath(
'//p/span/strong[contains(text(), "Responsibilities")]/ancestor::p/following-sibling::ul[1]/li/text()'
).getall())
contact = jobDetails.xpath(
'//p/span/strong[contains(text(), "How to Apply")]/ancestor::p/span/strong[contains(text(), "@")]/text()'
).get()
company = jobMeta.xpath('//span[last()]/a/text()').get()
applicationDetails = jobDetails.xpath(
'//p/span/strong[contains(text(), "How to Apply")]/ancestor::p/text()'
).getall()
if applicationDetails:
try:
deadline = ''.join(
[applicationDetails[-2], applicationDetails[-1]]).strip()
except IndexError:
deadline = "N/A"
else:
deadline = "N/A"
industry = jobMeta.xpath(
'//p/span[@class="entry-tags"]/a/text()').get()
country = 'Kenya'
requirements = 'N/A'
positionLevel = 'N/A'
technology = jobDetails.xpath('//p[3]/strong/text()').get()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = title
job["jobType"] = jobType
job["positionLevel"] = "N/A"
job["positions"] = 1
job["uploadDate"] = uploadTime
job["year"] = year
job["deadline"] = deadline
job["town"] = town
job["contact"] = contact
job["readvertised"] = "NO"
job["salary"] = salary
job["company"] = company
job["technology"] = technology
job["description"] = description
job["employmentType"] = jobType
job["skills"] = skills
job["industry"] = industry
job["responsibilities"] = responsibilities
job["requirements"] = requirements
job["country"] = country
return job
def parse(self, response):
valid_position = lambda position: position if position != -1 else 0
job = Job()
title = response.xpath('//div[@class="job-title"]/text()').get()
date = response.xpath('//div[@class="job-date"]/text()').get()
year = date.split('.')[-1].strip()
company = response.xpath('//div[@class="job-company"]/text()').get()
location = response.xpath('//div[@class="job-location"]/text()').get()
town = location.split(',')[0].strip()
country = location.split(',')[-1].strip()
description = self.clean_text(''.join(
response.xpath('//div[@class="job-desc"]/p/text()').getall()))
sumPos = valid_position(description.find('JOB SUMMARY'))
respPos = valid_position(description.find('RESPONSIBILITIES'))
skillPos = valid_position(description.find('REQUIRED SKILLS'))
eduPos = valid_position(description.find('REQUIRED EDUCATION'))
try:
jobDesc = response.xpath('substring("{}", {}, {})'.format(
description, sumPos, (respPos - sumPos))).get()
except:
jobDesc = ''
try:
skills = response.xpath('substring("{}", {}, {})'.format(
description, skillPos, (eduPos - skillPos))).get()
except:
skills = ''
try:
education = response.xpath('substring("{}", {})'.format(
description, eduPos)).get()
except:
education = ''
try:
reponsibilities = response.xpath('substring("{}", {}, {})'.format(
description, respPos, (skillPos - respPos))).get()
except:
reponsibilities = ''
contact = response.xpath(
'//div[@class="links"]/a[@class="view-job-link"]/@href').get()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = title
job["company"] = company
job["jobType"] = "Fulltime"
job["positionLevel"] = "N/A"
job["uploadDate"] = date
job["year"] = year
job["deadline"] = "N/A"
job["town"] = town
job["country"] = country
job["contact"] = contact
job["readvertised"] = "N"
job["technology"] = skills
job["description"] = jobDesc
job["employmentType"] = ''
job["skills"] = skills
job["industry"] = ''
job["responsibilities"] = reponsibilities
job["requirements"] = education
job["country"] = country
return job
def parse(self, response):
job = Job()
desc = response.xpath(
'//*[contains(text(), "Description")]/following::p[1]/text() | //div[@id="carrerbox"]/descendant-or-self::div[@class="wpb_wrapper"]/p/strong/span[contains(text(), "Job description")]/following::p[1]/text()'
).get()
resp = ''.join(
response.xpath(
'//*[contains(text(), "Responsibilities")]/following::ul[1]/li/text() | //div[@class="jobs-subheading"]/span/strong[contains(text(), "Responsibilities")]/ancestor::div/following-sibling::div/ul[1]/li/div/p/text()'
).getall())
qualifications = ''.join(
response.xpath(
'//*[contains(text(), "Responsibilities")]/following::ul[2]/li/text() | //div[@class="jobs-subheading"]/span/strong[contains(text(), "Responsibilities")]/ancestor::div/following-sibling::div/ul[1]/li/div/p/text()'
).getall())
if qualifications.find("Degree") == -1:
education = "N/A"
else:
education = qualifications[qualifications.
find("Degree"):qualifications.find(".")]
contact = response.xpath(
'//p/strong[contains(text(), "@")]/text() | //p/span/strong[contains(text(), "How to Apply")]/following::p[1]/span/a/@href'
).get()
title = response.xpath(
'//h1[contains(@class, "entry-title")]/text()').get()
position = response.xpath(
'//div[@class="wpb_wrapper"]/p[contains(text(), "Position")]/text()'
).get()
if position is not None:
position = position.split(':')[-1].strip()
location = response.xpath(
'//div[@class="wpb_wrapper"]/p[contains(text(), "Location")]/text()'
).get()
if location is not None:
location = location.split(':')[-1].strip()
industry = response.xpath('//div[@class="row"]/p[1]/text()').get()
job["ID"] = 1
job["website"] = self.meta["name"]
job["url"] = response.url
job["jobTitle"] = title
job["company"] = title.split('Job')[-1]
job["jobType"] = "Fulltime"
job["positionLevel"] = position
job["uploadDate"] = "N/A"
job["year"] = "2020"
job["deadline"] = "N/A"
job["town"] = location
job["country"] = "Kenya"
job["contact"] = contact
job["readvertised"] = "N/A"
job["technology"] = resp
job["description"] = desc
job["employmentType"] = "Fulltime"
job["skills"] = qualifications
job["industry"] = industry
job["responsibilities"] = resp
job["requirements"] = education
job["country"] = "Kenya"
return job
