def parse(self, response):
questions = Selector(response).xpath('//div[@class="row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('a/@title').extract()[0]
item['url'] = question.xpath('a/@href').extract()[0]
item['company'] = " ".join(
question.xpath(
'div[@class="sjcl"]/span[@class="company"]/text()').
extract()[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath(
'div[@class="sjcl"]/span[@class="company"]/a/text()').
extract()[0].split())
yield item
questions = Selector(response).xpath('//div[@class=" row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('h2/a/@title').extract()[0]
item['url'] = question.xpath('h2/a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/a/text()').
extract()[0].split())
yield item
questions = Selector(response).xpath(
'//div[@class="row sjlast result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('a/@title').extract()[0]
item['url'] = question.xpath('a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('div[@class="sjcl"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('div[@class="sjcl"]/span/a/text()').extract(
)[0].split())
yield item
questions = Selector(response).xpath(
'//div[@class="lastRow row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('h2/a/@title').extract()[0]
item['url'] = question.xpath('h2/a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/a/text()').
extract()[0].split())
yield item
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.xpath('//div[@class="row result"]')
items = []
for site in sites:
item = IndeedItem(company='none')
item['job_title'] = site.xpath('h2/a/@title').extract()
item['link_url'] = site.xpath('h2/a/@href').extract()
# item['location'] = site.xpath(
# 'span[@class="location"]/span/text()').extract()
# Not all entries have a company
if site.xpath("span[@class='company']/text()").extract() == []:
item['company'] = [u'']
else:
item['company'] = site.xpath(
"span[@class='company']/text()").extract()
item['summary'] = site.xpath(
"//table/tr/td/span[@class='summary']").extract()
item['source'] = site.xpath(
"table/tr/td/span[@class='source']/text()").extract()
item['found_date'] = site.xpath(
"table/tr/td/span[@class='date']/text()").extract()
items.append(item)
print items
def parse_detail_page(self, response):
print("=" * 50)
print(response.url)
title = response.xpath('//b[@class="jobtitle"]/font/text()').extract_first()
company = response.xpath('//span[@class="company"]/text()').extract_first()
location = response.xpath('//span[@class="location"]/text()').extract_first()
summary = response.xpath('//span[@id="job_summary"]').extract()
print("title", title)
print("company", company)
print("location",location)
try:
reviews = response.xpath('//span[@class="slNoUnderline"]/text()').extract_first() # can be None
except IndexError:
reviews = ""
try:
salary = response.xpath('//span[@class="no-wrap"]/text()').extract_first().strip() # can be None
except:
salary = ""
item = IndeedItem()
item['title'] = title
item['company'] = company
item['reviews'] = reviews
item['location'] = location
item['salary'] = salary
item['summary'] = summary
yield item
def parse_indeed_results(self, response):
self.log("PAPA")
#LIMIT
"""
self.item_count += 1
if self.item_count > 10:
raise CloseSpider('item_exceeded')
"""
# To extract elements, add them here
item = IndeedItem()
#TITLE
title = response.xpath(
'//h3[contains(@class,"JobInfoHeader")]/text()').extract_first()
item['title'] = title.strip()
#COMPANY
company_data = response.xpath(
'//div[contains(@class,"InlineCompanyRating")]//text()').extract()
item['company'] = company_data[0].strip()
item['address'] = company_data[-1].strip()
#DESCRIPTION
description = response.xpath(
'//div[contains(@id,"jobDescriptionText")]//text()').extract()
description = ' '.join(description)
item['description'] = description.replace("\n", "").encode('utf-8')
yield item
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.xpath('//div[contains(@class,"row")]')
for site in sites:
item = IndeedItem()
company = site.xpath(
".//span[@class='company']//a/text()").extract_first()
if not company:
company = site.xpath(
".//span[@class='company']/text()").extract_first()
item['company'] = company.strip()
# title
title = site.xpath(
'.//a[@data-tn-element="jobTitle"]/@title[1]').extract_first()
item['title'] = title
# indeed url
link = site.xpath(
".//span[@class='company']//a/@href").extract_first()
if link:
item['link'] = 'https://www.indeed.com' + link
yield item
# what to crawl next
next_to_crawl = hxs.xpath(
'//span[@class="pn"]/parent::a/@href').extract()
for i in next_to_crawl:
url = response.urljoin(i)
yield Request(url)
def parse(self, response):
list = response.xpath("//div[contains(@class,'row')]")
for row in list:
title = row.xpath("//a[@data-tn-element='jobTitle']/@title").extract()
companyina = row.xpath("//span[@class='company']/a/text()").extract()
companynoa = row.xpath("//span[@class='company']/text()").extract()
location = row.xpath("//span[@class='location']/text()").extract()
ka = 0
kn = 0
for kn in range(len(companynoa)):
if companynoa[kn] == '\n ':
companynoa[kn] = companyina[ka].strip(' \n')
ka += 1
else:
companynoa[kn] = companynoa[ka].strip(' \n')
kn += 1
company = companynoa
item = IndeedItem()
item['title'] = title
item['company'] = company
item['location'] = location
yield item
def process_spider_output(self, response, result, spider):
context = getattr(spider, 'context', {})
visited_ids = context.setdefault(self.CONTEXT_KEY, {})
ret = []
for x in result:
visited = False
if isinstance(x, Request):
if self.FILTER_VISITED in x.meta:
visit_id = self._visited_id(x)
if visit_id in visited_ids:
log.msg("Ignoring already visited: %s" % x.url,
level=log.INFO,
spider=spider)
visited = True
elif isinstance(x, BaseItem):
visit_id = self._visited_id(response.request)
if visit_id:
visited_ids[visit_id] = True
x['visit_id'] = visit_id
x['visit_status'] = 'new'
if visited:
ret.append(IndeedItem(visit_id=visit_id, visit_status='old'))
else:
ret.append(x)
return ret
def parse(self, response):
for clickCard in response.xpath(
'//div[@class="jobsearch-SerpJobCard unifiedRow row result"]'):
# 初始化Item
items = IndeedItem()
self.Q.put('Initialized......')
# jobTitle
items['jobTitle'] = clickCard.xpath('.//h2/a/@title').extract()[0]
self.Q.put('title parsed......')
# companyName
if clickCard.xpath('.//div/span[@class="company"]/text()').extract(
)[0].strip() == '':
items['companyName'] = clickCard.xpath(
'.//div/span[@class="company"]/a/text()').extract(
)[0].strip()
else:
items['companyName'] = clickCard.xpath(
'.//div/span[@class="company"]/text()').extract()[0].strip(
)
self.Q.put('companyName parsed......')
# url
items['url'] = clickCard.xpath('.//h2/a/@href').extract()[0]
self.Q.put('url parsed......')
self.Q.put(
f"\n{items['jobTitle']}\n{items['companyName']}\n{items['url']}\n"
)
yield items
def parse_item(self, response):
self.log('\n Crawling %s\n' % response.url)
hxs = HtmlXPathSelector(response)
sites = hxs.select("//div[@class='row ' or @class='row lastRow']")
#sites = hxs.select("//div[@class='row ']")
items = []
for site in sites:
item = IndeedItem(company='none')
item['job_title'] = site.select('h2/a/@title').extract()
link_url= site.select('h2/a/@href').extract()
item['link_url'] = link_url
item['crawl_url'] = response.url
item['location'] = site.select("span[@class='location']/text()").extract()
# Not all entries have a company
if site.select("span[@class='company']/text()").extract() == []:
item['company'] = [u'']
else:
item['company'] = site.select("span[@class='company']/text()").extract()
item['summary'] = site.select("//table/tr/td/span[@class='summary']").extract()
item['source'] = site.select("table/tr/td/span[@class='source']/text()").extract()
item['found_date'] = site.select("table/tr/td/span[@class='date']/text()").extract()
#item['source_url'] = self.get_source(link_url)
request = Request("http://www.indeed.com" + item['link_url'][0], callback=self.parse_next_site)
request.meta['item'] = item
yield request
items.append(item)
return
def parse(self, response):
item = IndeedItem()
company = response.xpath("""//*[@class="company"]//text()""").extract()
company = [i.strip() for i in company if i.strip()]
item['company'] = company
yield item
def parse_individual_job(self, response):
job_title = response.xpath(
'//h3[@class="icl-u-xs-mb--xs icl-u-xs-mt--none jobsearch-JobInfoHeader-title"]/text()'
).extract()
company_name = response.xpath(
'//div[@class="icl-u-lg-mr--sm icl-u-xs-mr--xs"]//text()').extract(
)[0]
location = response.xpath(
'//div[@class="jobsearch-InlineCompanyRating icl-u-xs-mt--xs jobsearch-DesktopStickyContainer-companyrating"]/div'
).extract()[-1].replace('<div>', '').replace('</div>', '')
salary = response.xpath(
'//span[@class="icl-u-xs-mr--xs"]/text()').extract_first()
job_type = response.xpath(
'//span[@class="jobsearch-JobMetadataHeader-item icl-u-xs-mt--xs"]/text()'
).extract_first()
job_summary = response.xpath(
'//div[@class="jobsearch-jobDescriptionText"]//text()').extract()
job_headings_text = response.xpath(
'//div[@class="jobsearch-jobDescriptionText"]/p/b//text()'
).extract()
job_bullets_text = response.xpath(
'//div[@class="jobsearch-jobDescriptionText"]/ul/li/text()'
).extract()
day_posted = response.xpath(
'//div[@class="jobsearch-JobMetadataFooter"]/text()'
).extract_first().replace(' - ', '')
try:
num_ratings = int(
response.xpath(
'//div[@class="icl-Ratings icl-Ratings--gold icl-Ratings--sm"]/meta/@content'
).extract()[1])
except Exception:
num_ratings = 0
try:
rating_out_of_5 = float(
response.xpath(
'//div[@class="icl-Ratings icl-Ratings--gold icl-Ratings--sm"]/meta/@content'
).extract()[0])
except Exception:
rating_out_of_5 = None
item = IndeedItem()
item['job_title'] = job_title
item['company_name'] = company_name
item['location'] = location
item['salary'] = salary
item['job_type'] = job_type
item['job_summary'] = job_summary
item['job_headings_text'] = job_headings_text
item['job_bullets_text'] = job_bullets_text
item['num_ratings'] = num_ratings
item['rating_out_of_5'] = rating_out_of_5
item['day_posted'] = day_posted
yield item
def parse_data(self, response):
#/'//span[@class="company"]/span'
#//h2/a/@title'
titles = response.xpath('//h2/a/@title').extract()
links = response.xpath('//h2/a/@href').extract()
companies = response.xpath('//span[@class="company"]/span').extract()
for title, link, company in zip(titles, links, companies):
item = IndeedItem()
item['title'] = title
item['link'] = link
item['company'] = bs(company).get_text().strip()
yield item
def store_item(self, data_dict):
item = IndeedItem()
# Raw scraped information
item['search_page_url'] = data_dict['search_page_url']
item['indeed_url'] = data_dict['indeed_url']
item['job_title'] = data_dict['job_title']
item['company_name'] = data_dict['company_name']
item['company_url'] = data_dict['company_url']
item['company_reviews'] = data_dict['company_reviews']
item['job_location'] = data_dict['job_location']
item['job_description'] = data_dict['job_description']
item['original_url'] = data_dict['original_url']
item['posted_when'] = data_dict['posted_when']
item['salary'] = data_dict['salary']
# Calculated information
parsed = urlparse(data_dict['search_page_url'])
item['search_location'] = unquote(parse_qs(parsed.query).get('l')[0])
parsed = urlparse(data_dict['indeed_url'])
try:
item['indeed_job_key'] = parse_qs(parsed.query).get('jk')[0]
except (TypeError, KeyError):
logging.error(f'Problem with {data_dict["indeed_url"]}')
if data_dict['company_reviews']:
num_stars, _, num_reviews = re.findall(
r'^([\d.]+) out of (\d) from ([\d,]+) employee rating',
data_dict['company_reviews'])[0]
item['num_stars'] = float(num_stars)
item['num_reviews'] = int(num_reviews.replace(',', ''))
if data_dict['salary']:
salary_range = re.findall(r'\$([\d,]+)', data_dict['salary'])
job_salary_low = salary_range[0]
job_salary_high = salary_range[-1]
item['job_salary_low'] = int(job_salary_low.replace(',', ''))
item['job_salary_high'] = int(job_salary_high.replace(',', ''))
if data_dict['posted_when']:
if data_dict['posted_when'] in ['Just posted', 'Today']:
days_ago = 0
else:
days_ago = int(
re.findall(r'(\d+)', data_dict['posted_when'])[0])
post_date = datetime.datetime.now() - datetime.timedelta(
days=days_ago)
item['post_date'] = post_date.date()
return item
def parse_data(self, response):
titles = response.xpath('//h2/a/@title').extract()
links = response.xpath('//h2/a/@href').extract()
companies = response.xpath('//span[@class="company"]/span').extract()
for title, link, comp in zip(titles, links, companies):
item = IndeedItem()
item['title'] = title
abs_url = response.urljoin(link)
item['url'] = abs_url
item['company'] = bs(comp).get_text().strip()
request = scrapy.Request(abs_url, callback=self.parse_job)
request.meta['item'] = item
yield request
def parse(self, response):
self.driver.get(response.url)
urls = []
for i in range(1, 20):
# self.driver.get(response.url)
response = TextResponse(url=self.driver.current_url,
body=self.driver.page_source,
encoding='utf-8')
self.driver.implicitly_wait(10)
for j in range(1, 31):
result = response.xpath('//*[@class="col-md-9"]/div[1]/div[' +
str(j) + ']/h3/a/@href')
urls.extend(result)
next_page = self.driver.find_element_by_xpath(
'//*[@title="Go to next page"]')
next_page.click()
for href in urls:
print href
url = href.extract()
self.driver.get(url)
response = TextResponse(url=self.driver.current_url,
body=self.driver.page_source,
encoding='utf-8')
item = IndeedItem()
for sel in response.xpath('//div[@class="col-md-5 col-lg-6"]'):
item['job_title'] = sel.xpath(
'//div[@class="col-md-5 col-lg-6"]/h1/text()').extract()
item['location'] = sel.xpath(
'//div[@class="col-md-5 col-lg-6"]/ul/li[2]/text()'
).extract()
item['company_name'] = sel.xpath(
'//div[@class="col-md-5 col-lg-6"]/ul/li[1]/a/text()'
).extract()
for sel_1 in response.xpath('//*[@id="bd"]/div/div[1]'):
item['job_type'] = sel_1.xpath(
'//div[2]/div/div[2]/span/text()').extract()
item['job_salary'] = sel_1.xpath(
'//div[3]/div/div[2]/span/text()').extract()
yield item
self.driver.close()
def parse_item(self, response):
print(response)
print('\n Crawling %s\n' % response.url)
hxs = Selector(response)
sites = hxs.select("//div[@class=' row result'] | //div[@class='row result'] | //div[@class='lastRow row result'] | //div[@class='row sjlast result']")
print (len(sites))
items = []
#--------------------------------------------------------------------------------------------#
for site in sites:
item = IndeedItem(company='none')
#print(site.select("descendant::a[@data-tn-element='jobTitle']/@href").extract())
item['job_title'] = site.select("descendant::a[@data-tn-element='jobTitle']/text()").extract()
link_url= site.select("descendant::a[@data-tn-element='jobTitle']/@href").extract()
item['link_url'] = link_url[0]
item['crawl_url'] = response.url
# Not all entries have a company
if site.select("descendant::span[@class='company']/span/text()").extract() == []:
if site.select("descendant::span[@class='company']/span/a/text()").extract() == []:
if len(site.select("descendant::span[@class='company']/a/text()").extract()) == 1:
item['company'] = site.select("descendant::span[@class='company']/a/text()").extract()
else:
item['company'] = site.select("descendant::span[@class='company']/text()").extract()
else:
item['company'] = site.select("descendant::span[@class='company']/a/text()").extract()
item['salary'] = site.select("descendant::div[@class='sjcl']/div/text()").extract()
item['location'] = site.select("descendant::span[@class='location']/text()").extract()
else:
if len(site.select("descendant::span[@class='company']/span/a/text()").extract()) == 1:
item['company'] = site.select("descendant::span[@class='company']/span/a/text()").extract()
else:
item['company'] = site.select("descendant::span[@class='company']/span/text()").extract()
item['salary'] = site.select("descendant::td[@class='snip']/nobr/text()").extract()
item['location'] = site.select("descendant::span[@class='location']/span/text()").extract()
tempSource = str(site.select("descendant::div[@class='result-link-bar']/script/text()").extract()[0]).split('=',1)
tempSource = tempSource[1]
tempSource = json.loads(tempSource[:-1])
try:
item['source'] = tempSource['source']
except KeyError, e:
item['source'] = []
try:
item['sponsored'] = tempSource['sponsored']
except KeyError, e:
item['sponsored'] = []
def parse_item(self, response):
'''
import pdb
pdb.set_trace()
'''
self.log('\n Crawling %s\n' % response.url)
hxs = HtmlXPathSelector(response)
sites = hxs.select("//div[@class='row ' or @class='row lastRow']")
#sites = hxs.select("//div[@class='row ']")
items = []
#Skip top two sponsored ads
for site in sites[:-2]:
item = IndeedItem(company='none')
item['job_title'] = site.select('h2/a/@title').extract()
link_url= site.select('h2/a/@href').extract()
item['link_url'] = link_url
item['crawl_url'] = response.url
item['location'] = site.select("span[@itemprop='jobLocation']/span[@class='location']/span[@itemprop='addressLocality']/text()").extract()
# Not all entries have a company
company_name = site.select("span[@class='company']/span[@itemprop='name']/text()").extract()
if company_name == []:
item['company'] = [u'']
else:
item['company'] = company_name
item['summary'] =site.select("table/tr/td/div/span[@class='summary']/text()").extract()
#item['source'] = site.select("table/tr/td/span[@class='source']/text()").extract()
item['found_date'] =site.select("table/tr/td/span[@class='date']/text()").extract()
#item['source_url'] = self.get_source(link_url)
if len(item['link_url']):
request = Request("http://www.indeed.com" + item['link_url'][0], callback=self.parse_next_site)
request.meta['item'] = item
yield request
return
def parse_jobs(self, response):
for sel in response.xpath("//div[contains(@class, 'row')]"):
items = []
jobs = sel.xpath(
'normalize-space(//a[contains(@data-tn-element, "jobTitle")])'
).extract()
city = sel.xpath(
'normalize-space(//span[@class="location"])').extract()
company = sel.xpath(
'normalize-space(//span[@class="company"]|//span[@itemprop = "hiringOrganization"])'
).extract()
description = sel.xpath(
'normalize-space(//span[@class="summary"])').extract()
for j, c, co, d in zip(jobs, city, company, description):
position = IndeedItem()
position['jobs'] = j.strip()
position['city'] = c.strip()
position['company'] = co.strip()
position['description'] = d.strip()
items.append(position)
return items
def parse(self, response):
jobs = Selector(response).xpath('//*[@id="resultsCol"]/div[@class=" row result"]')
file_path = os.path.join(os.getcwd(), 'items.csv')
job_data = []
mail_msg = ''
with open(file_path, 'r+') as data_file:
f_csv = csv.DictReader(data_file)
next(f_csv)
for row in f_csv:
job_data.append(row['url'])
for job in jobs:
item = IndeedItem()
item['title'] = job.xpath('h2/a[@class="turnstileLink"]/text()').extract()[0]
item['url'] = 'http://www.indeed.com.mx' + job.xpath('h2/a[@class="turnstileLink"]/@href').extract()[0]
if item['url'] not in job_data:
data_file.write(item['url'] + ',' + item['title'] + '\n')
mail_msg += '%s - %s \n\n' % (item['title'], item['url'] )
if mail_msg != '':
send_email(mail_msg)
def parse_item(self, response):
self.log('\n Crawling %s\n' % response.url)
hxs = Selector(response)
sites = hxs.xpath(
"//div[@class=' row result' or @class='lastRow row result' or @class='row sjlast result' or @class='row result']"
)
items = []
for site in sites:
item = IndeedItem(company='none')
item['job_title'] = site.xpath('h2/a/@title').extract()
link_url = site.xpath('h2/a/@href').extract()
item['link_url'] = link_url
item['crawl_url'] = response.url
item['location'] = site.xpath(
"span[@itemprop='jobLocation']//text()").extract()
# not all entries have a company name
if site.xpath("span[@class='company']//text()").extract() == []:
item['company'] = [u'']
else:
item['company'] = site.xpath(
"span[@class='company']//text()").extract()
item['summary'] = site.xpath(
"table//span[@class='summary']/text()").extract()
item['found_date'] = site.xpath(
"table/tr/td//span[@class='date']/text()").extract()
request = Request("http://www.indeed.com" +
item['link_url'][0],
callback=self.parse_next_site)
request.meta['item'] = item
yield request
items.append(item)
return item
return item
def parse_single(self, response):
reviews = response.xpath('//div[@class = "cmp-Review"]')
company = response.xpath('//div[@class = "cmp-CompactHeaderLayout-nameContainer"]//text()').extract_first()
for review in reviews:
item = IndeedItem()
item['company'] = company
item['rating'] = review.xpath(".//div[@class = 'cmp-ReviewRating-text']/text()").extract_first()
item['date'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[last()]").extract_first()
item['content'] = review.xpath(".//span[@itemprop = 'reviewBody']//span[@class = 'cmp-NewLineToBr-text']/text()").extract()
item['position'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']//meta[@itemprop='name']/@content").extract_first()
if len(review.xpath(".//div[@class = 'cmp-Review-title']/text()")):
item['title'] = review.xpath(".//div[@class = 'cmp-Review-title']/text()").extract_first()
else:
item['title'] = review.xpath(".//a[@class = 'cmp-Review-titleLink']/text()").extract_first()
if len(review.xpath(".//a[@class = 'cmp-ReviewAuthor-link']")) == 2 :
item['location'] = review.xpath(".//a[@class = 'cmp-ReviewAuthor-link'][2]/text()").extract_first()
item['status'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[2]").extract_first()
elif len(review.xpath(".//a[@class = 'cmp-ReviewAuthor-link']")) == 1:
if review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[last()-2]").extract_first() != ' - ':
item['location'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[last()-2]").extract_first()
item['status'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[last()-4]").extract_first()
else:
item['location'] = review.xpath(".//a[@class = 'cmp-ReviewAuthor-link'][1]/text()").extract_first()
item['status'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[3]").extract_first()
else:
item['location'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[5]").extract_first()
item['status'] = review.xpath(".//span[@class = 'cmp-ReviewAuthor']/text()[3]").extract_first()
subrating = review.xpath(".//div[@class = 'cmp-SubRating']//div[@class = 'cmp-RatingStars-starsFilled']/@style").extract()
item['work_life_rating'] = subrating[0]
item['benefits_rating'] = subrating[1]
item['security_rating'] = subrating[2]
item['management_rating'] = subrating[3]
item['culture_rating'] = subrating[4]
# 3px=0
# 15px=1
# 27px=2
# 39px=3
# 51px=4
# 63px=5
if len(review.xpath(".//div[@class = 'cmp-ReviewProsCons-prosText']//span[@class = 'cmp-NewLineToBr-text']/text()")):
item['Pros'] = review.xpath(".//div[@class = 'cmp-ReviewProsCons-prosText']//span[@class = 'cmp-NewLineToBr-text']/text()").extract_first()
else:
item['Pros'] = 'NaN'
if len(review.xpath(".//div[@class = 'cmp-ReviewProsCons-consText']//span[@class = 'cmp-NewLineToBr-text']/text()")):
item['Cons'] = review.xpath(".//div[@class = 'cmp-ReviewProsCons-consText']//span[@class = 'cmp-NewLineToBr-text']/text()").extract_first()
else:
item['Cons'] = 'NaN'
if len(review.xpath(".//span[text()='Yes']//span[@class = 'cmp-StatelessReviewFeedbackButtons-count']/text()")):
item['helpful'] = review.xpath(".//span[text()='Yes']//span[@class = 'cmp-StatelessReviewFeedbackButtons-count']/text()").extract_first()
else:
item['helpful'] = 0
if len(review.xpath(".//span[text()='No']//span[@class = 'cmp-StatelessReviewFeedbackButtons-count']/text()")):
item['helpless'] = review.xpath(".//span[text()='No']//span[@class = 'cmp-StatelessReviewFeedbackButtons-count']/text()").extract_first()
else:
item['helpless'] = 0
yield item
if len(response.xpath("//a[@data-tn-element = 'next-page']/@href")):
next_url = response.xpath("//a[@data-tn-element = 'next-page']/@href").extract_first()
yield scrapy.Request("https://www.indeed.com" + next_url ,callback = self.parse_single)
def parse(self, response):
for x in range (0, 10):
range_lower = None
range_upper = None
job_title = None
job_description = None
job_location = None
job_company = None
job_date = None
salary_description = None
job_money_unchanged = None
job_title = response.xpath('//h2/a/text()')[x].extract()
job_description = response.css('span.summary::text')[x].extract()
job_location = response.css('span.location span::text')[x].extract()
job_company = None
job_date = response.css('span.date::text')[x].extract()
try:
job_money = response.css('td.snip nobr::text')[x].extract()
job_money = str(job_money)
job_money_unchanged = job_money
if re.search(r' a year', job_money):
job_money = job_money.split(' a year')[0]
salary_description = 'a year'
if re.search(r' an hour', job_money):
job_money = job_money.split(' an hour')[0]
salary_description = 'an hour'
if re.search(r'-', job_money):
range_lower = job_money.split(" - ")[0]
range_upper = job_money.split(" - ")[1]
except:
job_money = None
try:
job_company = response.xpath('//div['+ str(x+4) +']/span[1]/span/a/text()').extract_first()
if job_company == None:
job_company = response.xpath('//div['+ str(x+4) +']/span[1]/span/text()').extract_first()
if job_company == None:
job_company = "Nothing"
except:
job_company = None
try:
image_link = response.xpath('//div['+ str(x+4) +']/span[1]/span/a/@href').extract_first()
except:
image_link = None
half_link = response.xpath('//h2/a').xpath("@href")[x].extract()
full_link = "http://au.indeed.com" + half_link
item = IndeedItem()
global main_counter
main_counter = main_counter + 1
with open('./static/counter', 'w') as f:
f.write(str(main_counter))
item['jobNumber'] = main_counter
item['job_title'] = job_title
item['job_description'] = job_description
item['job_location'] = job_location
item['job_company'] = job_company
global loaded_date
item['job_date'] = loaded_date
item['job_money'] = job_money
item['range_upper'] = range_upper
item['job_money_unchanged'] = job_money_unchanged
item['range_lower'] = range_lower
item['salary_description'] = salary_description
item['image_link'] = image_link
request = scrapy.Request(full_link, callback=self.parse_original_url)
request.meta['item'] = item
yield request
def parse(self, response):
test = str(response.url)
yield IndeedItem(test=test)
def parse_item(self, response):
questions = Selector(response).xpath('//div[@class="row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('a/@title').extract()[0]
item['url'] = 'http://indeed.com' + question.xpath(
'a/@href').extract()[0]
item['company'] = " ".join(
question.xpath(
'div[@class="sjcl"]/span[@class="company"]/text()').
extract()[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath(
'div[@class="sjcl"]/span[@class="company"]/a/text()').
extract()[0].split())
item['words'] = text_cleaner(item['url'])
item['city'] = question.xpath(
'div[@class="sjcl"]/span[@class="location"]/text()').extract(
)[0]
item['city'], item['state'] = state_extract(item['city'], )
yield item
questions = Selector(response).xpath('//div[@class=" row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('h2/a/@title').extract()[0]
item['url'] = 'http://indeed.com' + question.xpath(
'h2/a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/a/text()').
extract()[0].split())
item['words'] = text_cleaner(item['url'])
item['city'] = question.xpath(
'span[@itemprop="jobLocation"]/span/span/text()').extract()[0]
item['city'], item['state'] = state_extract(item['city'], )
yield item
questions = Selector(response).xpath(
'//div[@class="row sjlast result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('a/@title').extract()[0]
item['url'] = 'http://indeed.com' + question.xpath(
'a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('div[@class="sjcl"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('div[@class="sjcl"]/span/a/text()').extract(
)[0].split())
item['words'] = text_cleaner(item['url'])
item['city'] = question.xpath(
'div[@class="sjcl"]/span[@class="location"]/text()').extract(
)[0]
item['city'], item['state'] = state_extract(item['city'], )
yield item
questions = Selector(response).xpath(
'//div[@class="lastRow row result"]')
for question in questions:
item = IndeedItem()
item['title'] = question.xpath('h2/a/@title').extract()[0]
item['url'] = 'http://indeed.com' + question.xpath(
'h2/a/@href').extract()[0]
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/text()').extract()
[0].split())
if not item['company']:
item['company'] = " ".join(
question.xpath('span[@class="company"]/span/a/text()').
extract()[0].split())
item['words'] = text_cleaner(item['url'])
item['city'] = question.xpath(
'span[@itemprop="jobLocation"]/span/span/text()').extract()[0]
item['city'], item['state'] = state_extract(item['city'], )
yield item
