def scrapEFSA():
print("#========================= EFSA SCRAPING =========================")
# Database connection and agency retrieval
efsaData = efsa.returnAgency('EFSA')
efsa_link = efsaData['link'][0]
efsa_id = efsaData['id'][0]
html = urllib.request.urlopen(efsa_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.findAll('div',attrs={'class':'jlr_right_hldr'})
for child in start:
jobTitle = child.p.string
jobLink = child.p.a.get('href')
jobDept = child.find('div',attrs={'class':'jlr_content_half jlr_content_right'}).p.span.next_element.next_element.next_element.string
print (jobTitle, jobLink,jobDept)
efsa.persist(int(efsa_id), str(jobTitle).strip(), '', jobDept, '', 'SA', jobLink, '', 'Other')
print("#======================== EFSA SCRAPING COMPLETE =================================")
def scrapEFSA():
print("#========================= EFSA SCRAPING =========================")
# Database connection and agency retrieval
efsaData = efsa.returnAgency('EFSA')
efsa_link = efsaData['link'][0]
efsa_id = efsaData['id'][0]
html = urllib.request.urlopen(efsa_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.findAll('div', attrs={'class': 'jlr_right_hldr'})
for child in start:
jobTitle = child.p.string
jobLink = child.p.a.get('href')
jobDept = child.find(
'div', attrs={
'class': 'jlr_content_half jlr_content_right'
}).p.span.next_element.next_element.next_element.string
print(jobTitle, jobLink, jobDept)
efsa.persist(int(efsa_id),
str(jobTitle).strip(), '', jobDept, '', 'SA', jobLink, '',
'Other')
print(
"#======================== EFSA SCRAPING COMPLETE ================================="
)
def scrapESMA():
print("#========================= ESMA SCRAPING =========================")
# Database connection and agency retrieval
esmaData = esma.returnAgency('ESMA')
esma_link = esmaData['link'][0]
esma_id = esmaData['id'][0]
html = urllib.request.urlopen(esma_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div',attrs={'class':'search-page_main'})
# Find the jobs table
Jobtable = (start.table.tbody.findAll('tr'))
for child in Jobtable:
titleSource = child.find('td',attrs={'class':'esma_library-title'})
jobCode = child.find('td',attrs={'class':'esma_library-ref'}).string
jobLink = titleSource.a.get('href')
jobTitle = titleSource.string
jobDeadline = data_format.dateFormatFull(re.sub('\D','',jobTitle))
jobType = data_format.typeOfGrade(jobCode)
print (jobTitle, jobCode, jobLink,jobDeadline,jobType)
esma.persist(int(esma_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink, '', jobType)
print("#========================ESMA SCRAPING COMPLETE=================================")
def scrapEMA():
print("#========================= EMA SCRAPING =========================")
# Database connection and agency retrieval
emaData = ema.returnAgency('EMA')
ema_link = emaData['link'][0]
ema_id = emaData['id'][0]
html = urllib.request.urlopen(ema_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div',attrs={'class':'main-col'})
# Find the jobs table
Jobtable = (start.find('table'))
for child in Jobtable.children:
if(child.find('td',attrs={'colspan':'top'})):
continue
jobTitle = child.td.string
jobCode = child.td.next_sibling.string
jobType = data_format.typeOfPost(jobCode)
jobLink = "http://www.ema.europa.eu/ema/" + child.td.next_sibling.next_sibling.a.get('href')
jobDeadline = data_format.dateFormatFull(child.td.next_sibling.next_sibling.next_sibling.string)
print(jobTitle,jobCode,jobType,jobLink,jobDeadline)
ema.persist(int(ema_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink, '', jobType)
print("#========================EMA SCRAPING COMPLETE=================================")
def scrapESMA():
print("#========================= ESMA SCRAPING =========================")
# Database connection and agency retrieval
esmaData = esma.returnAgency('ESMA')
esma_link = esmaData['link'][0]
esma_id = esmaData['id'][0]
html = urllib.request.urlopen(esma_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div', attrs={'class': 'search-page_main'})
# Find the jobs table
Jobtable = (start.table.tbody.findAll('tr'))
for child in Jobtable:
titleSource = child.find('td', attrs={'class': 'esma_library-title'})
jobCode = child.find('td', attrs={'class': 'esma_library-ref'}).string
jobLink = titleSource.a.get('href')
jobTitle = titleSource.string
jobDeadline = data_format.dateFormatFull(re.sub('\D', '', jobTitle))
jobType = data_format.typeOfGrade(jobCode)
print(jobTitle, jobCode, jobLink, jobDeadline, jobType)
esma.persist(int(esma_id),
str(jobTitle).strip(), '', '', jobCode, jobDeadline,
jobLink, '', jobType)
print(
"#========================ESMA SCRAPING COMPLETE================================="
)
def scrapCPVO():
print("#========================= CPVO SCRAPING =========================")
# Database connection and agency retrieval
cpvoData = cpvo.returnAgency('CPVO')
cpvo_link = cpvoData['link'][0]
cpvo_id = cpvoData['id'][0]
html = urllib.request.urlopen(cpvo_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('table',attrs={'summary':'Vacancies'})
# Find the jobs table
Jobtable = (start.findAll('tr'))
for child in Jobtable:
if(child.find('th',attrs={'id':'vacancy_title'})):
continue
#print (child)
jobTitle = child.td.a.string.strip()
jobLink = child.td.a.get('href')
jobCode = child.td.next_sibling.next_sibling.string.strip()
jobType = data_format.typeOfPost(jobCode)
jobDeadline = data_format.dateFormatFull(child.td.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.string.strip())
logging.debug (jobTitle,jobLink,jobCode,jobType,jobDeadline)
cpvo.persist(int(cpvo_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink, '', jobType)
print("#========================CPVO SCRAPING COMPLETE=================================")
def scrapSatCen():
print("#========================= SatCen SCRAPING =========================")
SatCenData = satcen.returnAgency('SATCEN')
SatCen_link = SatCenData['link'][0]
SatCen_id = SatCenData['id'][0]
SatCen_source = urllib.request.urlopen(SatCen_link)
#Retrieve the list of jobs as bs4 navigable string
soup = BeautifulSoup(SatCen_source,'html.parser')
#Convert to bytes
bytesEncoded = soup.encode('utf-8')
#Convert to string
stringDecoded = bytesEncoded.decode('utf-8')
#Convert to dictionary
jobsdict = json.loads(stringDecoded)
#Browse dictionaty and select available positions
for job in jobsdict:
if (job['Status']=='OPEN') and (job['InternalOnly'] == False):
link = 'https://apps.satcen.europa.eu/recruitment/#/vacancy/'+job['Id']
print(job['Reference'], job['ExpireOn'][:10],job['Title'],format.typeOfPost(job['TypePost']),job['WorkUnit'],link)
satcen.persist(SatCen_id, job['Title'],job['Reference'],job['WorkUnit'],'', job['ExpireOn'][:10],link,'', format.typeOfPost(job['TypePost']))
print("#========================SATCEN SCRAPING COMPLETE=================================")
def scrapETF():
print("#========================= ETF SCRAPING =========================")
# Database connection and agency retrieval
etfData = etf.returnAgency('ETF')
etf_link = etfData['link'][0]
etf_id = etfData['id'][0]
html = urllib.request.urlopen(etf_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div',attrs={'class':'content_group piclist_content'})
# Find the jobs table
Jobtable = start.find('div').div.ul
for child in Jobtable.children:
jobTitle = child.div.h2.string
jobLink = "http://www.etf.europa.eu" + child.div.p.a.get('href')
jobCode = child.div.p.a.string
jobDeadline = data_format.dateFormatFull(str(child.div.p)[12:22])
print (jobTitle, jobLink.replace(' ','%20'), jobCode, jobDeadline)
etf.persist(int(etf_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink.replace(' ','%20'), '', 'Other')
print("#======================== ETF SCRAPING COMPLETE =================================")
def scrapETF():
print("#========================= ETF SCRAPING =========================")
# Database connection and agency retrieval
etfData = etf.returnAgency('ETF')
etf_link = etfData['link'][0]
etf_id = etfData['id'][0]
html = urllib.request.urlopen(etf_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div', attrs={'class': 'content_group piclist_content'})
# Find the jobs table
Jobtable = start.find('div').div.ul
for child in Jobtable.children:
jobTitle = child.div.h2.string
jobLink = "http://www.etf.europa.eu" + child.div.p.a.get('href')
jobCode = child.div.p.a.string
jobDeadline = data_format.dateFormatFull(str(child.div.p)[12:22])
print(jobTitle, jobLink.replace(' ', '%20'), jobCode, jobDeadline)
etf.persist(int(etf_id),
str(jobTitle).strip(), '', '', jobCode, jobDeadline,
jobLink.replace(' ', '%20'), '', 'Other')
print(
"#======================== ETF SCRAPING COMPLETE ================================="
)
def scrapEIOPA():
print(
"#========================= EIOPA SCRAPING =========================")
# Database connection and agency retrieval
eiopaData = eiopa.returnAgency('EIOPA')
eiopa_link = eiopaData['link'][0]
eiopa_id = eiopaData['id'][0]
html = urllib.request.urlopen(eiopa_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('table', attrs={'class': 'ms-rteTable-EIOPATable'})
for tr in start.tbody:
if str(tr['class'][0]) == "ms-rteTableHeaderRow-EIOPATable":
continue
jobTitle = tr.th.next_sibling.a.string
jobLink = "https://eiopa.europa.eu/" + tr.th.next_sibling.a.get('href')
jobCode = str(re.match(r'(.*?)%20', jobLink).group(1)[29:])
jobType = data_format.typeOfPost(jobCode)
deadlinePosition = tr.td.next_sibling
if re.match('\w', jobTitle[0]) is None:
jobTitle = jobTitle[1:len(jobTitle)]
if (len(deadlinePosition.contents[0].string) > 2):
jobDeadline = deadlinePosition.contents[0].string
jobDeadline = str(jobDeadline).strip()
jobDeadline = data_format.dateFormatFull(jobDeadline[1:])
else:
extendedDeadlines = deadlinePosition.findAll('strong')
newDeadline = extendedDeadlines[len(extendedDeadlines) - 1].string
newDeadline = str(newDeadline.split(':')[1]).strip()
jobDeadline = data_format.dateFormatFull(newDeadline)
print(jobTitle, jobCode, jobType, jobDeadline)
eiopa.persist(int(eiopa_id), jobTitle, '', '', jobCode, jobDeadline,
jobLink, '', jobType)
print(
"#========================EIOPA SCRAPING COMPLETE================================="
)
#scrapEIOPA()
def scrapEBA():
print("#========================= EBA SCRAPING =========================")
# Database connection and agency retrieval
ebaData = eba.returnAgency('EBA')
eba_link = ebaData['link'][0]
eba_id = ebaData['id'][0]
pages = {"CA": "contract-agents", "TA": "temporary-agents", "SNE": "national-experts-on-secondment"}
for pairs in pages:
title = pairs.title().upper()
page_link = (eba_link + "/" + pages[title])
html = urllib.request.urlopen(page_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('table', attrs={'class': 'Tabular'})
today = datetime.datetime.today().date()
# Find the jobs table
Jobtable = (start.findAll('tr'))
for cell in Jobtable:
td = cell.findAll('td')
try:
status = td[3].string.strip()
rawDate = td[2].string
searchDate = re.match(r'(.*)at', rawDate)
date = data_format.dateFormatFull(searchDate.group(1).strip())
except:
continue
if (today < date) and (status == "ongoing"):
jobLink = eba_link[:24] + td[0].a.get('href')
jobTitle = td[0].string
jobCode = td[1].string.strip()
jobDeadline = date
jobType = title
print(jobCode, jobTitle, jobType, jobDeadline, jobLink)
eba.persist(int(eba_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink, '', jobType)
else:
continue
print("#========================EBA SCRAPING COMPLETE=================================")
def scrapBBI():
print("#========================= BBI SCRAPING =========================")
# Database connection and agency retrieval
bbiData = bbi.returnAgency('BBI')
bbi_link = bbiData['link'][0]
bbi_id = bbiData['id'][0]
html = urllib.request.urlopen(bbi_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('tbody',
attrs={'class': 'ui-datatable-data ui-widget-content'})
# Find the jobs table
Jobtable = (start.findAll('tr'))
for child in Jobtable:
jobCodeLocation = child.td.next_sibling
jobTitleLocation = jobCodeLocation.next_sibling
jobTypeLocation = jobTitleLocation.next_sibling
jobGradeLocation = jobTypeLocation.next_sibling
jobDeadlineLocation = jobGradeLocation.next_sibling
jobLinkLocation = jobDeadlineLocation.next_sibling
jobCode = jobCodeLocation.string
jobTitle = jobTitleLocation.string
jobType = data_format.typeOfPost(jobTypeLocation.string)
jobGrade = data_format.typeOfGrade(jobGradeLocation.string)
jobDeadline = data_format.dateFormatFull(
jobDeadlineLocation.string[:10])
jobLink = jobLinkLocation.a.get('href')
print(jobCode, jobTitle, jobType, jobGrade, jobDeadline, jobLink)
bbi.persist(int(bbi_id),
str(jobTitle).strip(), '', '', jobCode, jobDeadline,
jobLink, '', jobType)
print(
"#========================BBI SCRAPING COMPLETE================================="
)
def scrapEACEA():
print("#========================= EACEA SCRAPING =========================")
# Database connection and agency retrieval
eaceaData = eacea.returnAgency('EACEA')
eacea_link = eaceaData['link'][0]
eacea_id = eaceaData['id'][0]
html = urllib.request.urlopen(eacea_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('table',attrs={'class':'table table-striped table-hover views-table cols-4'})
# Find the jobs table
Jobtable = (start.find('tbody'))
rows = Jobtable.findAll('tr')
for posts in rows:
columns = posts.children
for tds in columns:
try:
status = tds.next_sibling.next_sibling.next_sibling.next_sibling.span.string
if (status == 'Open'):
jobLink = "http://eacea.ec.europa.eu"+ tds.a.get('href')
jobTitle = tds.a.string
deadline = tds.next_sibling.next_sibling.span.string
jobDeadline = data_format.dateFormatFull(deadline[:10])
if jobTitle.find('CA-FG')> 0:
jobType = "CA"
else:
jobType = "Other"
print(jobTitle, jobLink, jobType, jobDeadline)
eacea.persist(int(eacea_id), str(jobTitle).strip(), '', '', '', jobDeadline, jobLink, '', jobType)
else: continue
except:
continue
print("#========================EACEA SCRAPING COMPLETE=================================")
def scrapCDT():
print("#========================= CDT SCRAPING =========================")
# Database connection and agency retrieval
cdtData = cdt.returnAgency('CDT')
cdt_link = cdtData['link'][0]
cdt_id = cdtData['id'][0]
html = urllib.request.urlopen(cdt_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.findAll('div',
attrs={'class': 'ms-rtestate-read ms-rte-wpbox'})
#print (start[1])#.ul.li.p.div.span.font.string.strip())
for child in start:
jobTitle = child.span.attrs['title']
postType = jobTitle[:9].strip()
for post in child.ul:
try:
#print (child.ul)
job = post.find('h3')
jobCode = job.a.string.strip()
jobLink = "http://cdt.europa.eu" + job.a.get('href').replace(
' ', '%20')
jobTitle = post.find('p').div.span.font.string.strip()
jobType = data_format.typeOfPost(postType)
jobDeadline = data_format.dateFormatFull('SA')
print(jobCode, jobLink, jobTitle, jobType, jobDeadline)
cdt.persist(int(cdt_id),
str(jobTitle).strip(), '', '', jobCode,
jobDeadline, jobLink, '', jobType)
except:
continue
print(
"#========================CDT SCRAPING COMPLETE================================="
)
def scrapBBI():
print("#========================= BBI SCRAPING =========================")
# Database connection and agency retrieval
bbiData = bbi.returnAgency('BBI')
bbi_link = bbiData['link'][0]
bbi_id = bbiData['id'][0]
html = urllib.request.urlopen(bbi_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('tbody',attrs={'class':'ui-datatable-data ui-widget-content'})
# Find the jobs table
Jobtable = (start.findAll('tr'))
for child in Jobtable:
jobCodeLocation = child.td.next_sibling
jobTitleLocation = jobCodeLocation.next_sibling
jobTypeLocation = jobTitleLocation.next_sibling
jobGradeLocation = jobTypeLocation.next_sibling
jobDeadlineLocation = jobGradeLocation.next_sibling
jobLinkLocation = jobDeadlineLocation.next_sibling
jobCode = jobCodeLocation.string
jobTitle = jobTitleLocation.string
jobType = data_format.typeOfPost(jobTypeLocation.string)
jobGrade = data_format.typeOfGrade(jobGradeLocation.string)
jobDeadline = data_format.dateFormatFull(jobDeadlineLocation.string[:10])
jobLink = jobLinkLocation.a.get('href')
print (jobCode,jobTitle,jobType,jobGrade,jobDeadline,jobLink)
bbi.persist(int(bbi_id), str(jobTitle).strip(), '', '', jobCode, jobDeadline, jobLink, '', jobType)
print("#========================BBI SCRAPING COMPLETE=================================")
def scrapF4E():
print("#========================= F4E SCRAPING =========================")
F4EData = F4E.returnAgency('F4E')
F4E_link = F4EData['link'][0]
F4E_id = F4EData['id'][0]
html = urllib.request.urlopen(F4E_link)
soup = BeautifulSoup(html, "html.parser")
start = soup.findAll(attrs={"class": re.compile("^careersPurple2")})
for contractType in start:
deadline = jobTitle = jobCode = jobLink = ''
contract = data_format.typeOfPost(contractType.a.string)
jobInfo = contractType.next_sibling.next_sibling
try:
deadline = data_format.dateFormatFull(
jobInfo.find(attrs={
"class": "careersDate"
}).span.string)
jobTitle = jobInfo.find(attrs={"class": "careersTitle"}).string
jobCode = jobInfo.find(attrs={"class": "pdf"}).string
jobLink = "http://fusionforenergy.europa.eu/careers/vacancies/" + jobInfo.find(
attrs={
"class": "pdf"
}).get("href")
print(deadline, jobTitle.strip(), jobCode, jobLink, contract)
F4E.persist(F4E_id, jobTitle.strip(), jobCode, '', '', deadline,
jobLink, '', contract)
except:
pass
print(
"#========================F4E SCRAPING COMPLETE================================="
)
def scrapEMA():
print("#========================= EMA SCRAPING =========================")
# Database connection and agency retrieval
emaData = ema.returnAgency('EMA')
ema_link = emaData['link'][0]
ema_id = emaData['id'][0]
html = urllib.request.urlopen(ema_link)
soup = BeautifulSoup(html, "html.parser")
# Create the soup
start = soup.find('div', attrs={'class': 'main-col'})
# Find the jobs table
Jobtable = (start.find('table'))
for child in Jobtable.children:
if (child.find('td', attrs={'colspan': 'top'})):
continue
jobTitle = child.td.string
jobCode = child.td.next_sibling.string
jobType = data_format.typeOfPost(jobCode)
jobLink = "http://www.ema.europa.eu/ema/" + child.td.next_sibling.next_sibling.a.get(
'href')
jobDeadline = data_format.dateFormatFull(
child.td.next_sibling.next_sibling.next_sibling.string)
print(jobTitle, jobCode, jobType, jobLink, jobDeadline)
ema.persist(int(ema_id),
str(jobTitle).strip(), '', '', jobCode, jobDeadline,
jobLink, '', jobType)
print(
"#========================EMA SCRAPING COMPLETE================================="
)
def scrapEMSA():
print("#========================= EMSA SCRAPING =========================")
emsaData = emsa.returnAgency('EMSA')
emsa_link = emsaData['link'][0]
emsa_id = emsaData['id'][0]
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36"
headers = { 'User-Agent' : user_agent }
data = ''
data = data.encode('ascii')
req = urllib.request.Request(emsa_link,data,headers)
with urllib.request.urlopen(req) as response:
html = response.read()
soup = BeautifulSoup(html, "html.parser")
# Find the first ad
start = soup.findAll(attrs={"class":"sectiontableentry"})
# Iterate through the tables
for cell in start:
ad_code = cell.find("th").get_text()
print ("Job Code:" + ad_code.strip())
ad_url = "http://www.emsa.europa.eu"+cell.find('a').get('href')
print ("Job URL:" + ad_url)
count = 0
for ad in cell.findAll("td"):
if count == 0 :
ad_description = ad.get_text()
print ("description: " + ad_description)
if count == 2 :
ad_deadline = ad.get_text()
print ("deadline: " + ad_deadline)
count = count + 1
# Convert date
try:
date_object = datetime.strptime(ad_deadline, '%d.%m.%Y')
deadline = date_object.date()
#print (deadline)
except:
print ("could not modify " + deadline)
pass
ad_raw = ad_code +" "+ ad_description
# Identify type
jobType = data_format.typeOfGrade(ad_raw)
print (jobType)
# Insert job details in database
emsa.persist(int(emsa_id), str(ad_description).strip(), '', '', str(ad_code).strip(), deadline, str(ad_url).strip(), '', jobType)
print("#========================EMSA SCRAPING COMPLETE=================================")
def scrapEDA():
print("#========================= EDA SCRAPING =========================")
edaData = eda.returnAgency('EDA')
eda_link = edaData['link'][0]
eda_id = edaData['id'][0]
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36"
headers = {'User-Agent': user_agent}
data = ''
data = data.encode('ascii')
req = urllib.request.Request(eda_link, data, headers)
#print(emsa_link)
with urllib.request.urlopen(req) as response:
html = response.read()
soup = BeautifulSoup(html, "html.parser")
# Iterate through the internal groups
for post_type in soup.find_all("h4"):
internal_type = post_type.contents[0].strip()
if internal_type not in ('Temporary Agents', 'Contractual Agents',
'Seconded National Experts'):
continue
elif internal_type == 'Temporary Agents':
job_type = 'TA'
elif internal_type == 'Contractual Agents':
job_type = 'CA'
else:
job_type = 'SNE'
print(post_type.contents[0])
internals = post_type.next_element.next_element.next_element.find_all(
"li")
#try:
# Iterate the URLs for each TA post
for post in internals:
ta_link = eda_link + post.find('a').get("href")
ta_req = urllib.request.Request(ta_link, data, headers)
with urllib.request.urlopen(ta_req) as response:
ta_html = response.read()
ta_soup = BeautifulSoup(ta_html, "html.parser")
#Link
print(ta_link)
#Post
post_title = ta_soup.findAll(
attrs={"id": "cphMain_VacNotice_LabPost"
})[0].contents[0].strip()
print(post_title)
#Grade
post_grade = ta_soup.findAll(
attrs={"id": "cphMain_VacNotice_LabGrade"
})[0].contents[0].strip()
print(post_grade)
#Deadline
post_deadline = ta_soup.findAll(
attrs={"id": "cphMain_VacNotice_LabPublicationDateEnd"})
print(post_deadline[0].contents[0].strip() + "\n")
# Convert date
try:
date_object = datetime.strptime(
post_deadline[0].contents[0].strip(), '%d %B %Y')
deadline = date_object.date()
#print (deadline)
except:
print("could not modify " + str(post_deadline))
pass
# Insert job details in database
eda.persist(int(eda_id),
str(post_title).strip(), str(post_grade), '', '',
deadline,
str(ta_link).strip(), '', job_type)
#except:
# pass
print(
"#========================EDA SCRAPING COMPLETE================================="
)
def scrapEMSA():
print("#========================= EMSA SCRAPING =========================")
emsaData = emsa.returnAgency('EMSA')
emsa_link = emsaData['link'][0]
emsa_id = emsaData['id'][0]
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36"
headers = {'User-Agent': user_agent}
data = ''
data = data.encode('ascii')
req = urllib.request.Request(emsa_link, data, headers)
with urllib.request.urlopen(req) as response:
html = response.read()
soup = BeautifulSoup(html, "html.parser")
# Find the first ad
start = soup.findAll(attrs={"class": "sectiontableentry"})
# Iterate through the tables
for cell in start:
ad_code = cell.find("th").get_text()
print("Job Code:" + ad_code.strip())
ad_url = "http://www.emsa.europa.eu" + cell.find('a').get('href')
print("Job URL:" + ad_url)
count = 0
for ad in cell.findAll("td"):
if count == 0:
ad_description = ad.get_text()
print("description: " + ad_description)
if count == 2:
ad_deadline = ad.get_text()
print("deadline: " + ad_deadline)
count = count + 1
# Convert date
try:
date_object = datetime.strptime(ad_deadline, '%d.%m.%Y')
deadline = date_object.date()
#print (deadline)
except:
print("could not modify " + deadline)
pass
ad_raw = ad_code + " " + ad_description
# Identify type
jobType = data_format.typeOfGrade(ad_raw)
print(jobType)
# Insert job details in database
emsa.persist(int(emsa_id),
str(ad_description).strip(), '', '',
str(ad_code).strip(), deadline,
str(ad_url).strip(), '', jobType)
print(
"#========================EMSA SCRAPING COMPLETE================================="
)
def scrapEUROPOL():
print(
"#========================= EUROPOL SCRAPING ========================="
)
europolData = europol.returnAgency('EUROPOL')
europol_link = europolData['link'][0]
europol_id = europolData['id'][0]
html = urllib.request.urlopen(europol_link)
soup = BeautifulSoup(html, "html.parser")
def dateFormatFull(inputDate):
dnotz = None
for form in [
'%d %b %Y', '%d %b %y', '%d %B %Y', '%d/%m/%Y', '%d.%m.%Y'
]:
try:
dnotz = datetime.strptime(inputDate, form).date()
return str(dnotz)
except:
continue
if dnotz is None:
print('Bad Date:', inputDate)
return str(inputDate)
# Find all ads
start = soup.findAll(attrs={"class": re.compile("^views-row views-row-")})
#print ("posts found " + str(len(start)))
# Iterate through the divs
for advert in start:
try:
deadline = advert.find(attrs={
"class": "views-field views-field-deadline"
}).findAll('span')[1].get_text()
deadlineFormatted = dateFormatFull(deadline)
print("Deadline:", dateFormatFull(deadline))
print(
"Contract Type:",
advert.find(attrs={
"class": "views-field views-field-contract-type"
}).find('span').get_text())
jobTitle = advert.find("a").get_text()
print("Title:", jobTitle)
dept = advert.find(attrs={
"class": "views-field views-field-department"
}).find('span').get_text()
print("Department:", dept)
title = advert.find(
attrs={
"class": "views-field views-field-reference-number"
}).find('span').get_text()
print("Reference Number:", title)
url = "http://www.europol.europa.eu" + advert.find("a").get("href")
print("Link:", url)
except:
continue
if re.search('(AD+\d{1,2}?|AD +\d{1,2}?|TA)', title) is not None:
jobType = "AD"
elif re.search('(AST+\d{1,2}?|AST +\d{1,2}?)', title) is not None:
jobType = "AST"
elif re.search('(FG+\d|FG+III|FG+IV|Function Groups|CA)',
title) is not None:
jobType = "CA"
elif re.search('(trainee)', title, re.IGNORECASE) is not None:
jobType = "Trainee"
elif re.search('(SNE|Seconded)', title, re.IGNORECASE) is not None:
jobType = "SNE"
else:
jobType = "Other"
print(int(europol_id),
str(jobTitle).strip(), '',
str(dept).strip(),
str(title).strip(), deadlineFormatted,
str(url).strip(), '', jobType)
europol.persist(int(europol_id),
str(jobTitle).strip(), '',
str(dept).strip(),
str(title).strip(), deadlineFormatted,
str(url).strip(), '', jobType)
print(
"#========================EUROPOL SCRAPING COMPLETE================================="
)
def scrapEPSO():
print("#========================= EPSO SCRAPING =========================")
epsoData = epso.returnAgency('EPSO')
epso_link = epsoData['link'][0]
html = urllib.request.urlopen(epso_link)
text = html.read().decode('utf-8')
soup = BeautifulSoup(text, "html.parser")
#Initiate scrap
start = soup.find(attrs={"class": "view-content"})
page = 0
while (start is not None):
table = start.tbody.findAll("tr")
for tr in table:
# Retrieve job information
print(
tr.find(attrs={
"class": "views-field views-field-field-epso-locations"
}).get_text())
jobTitle = tr.find(attrs={
"class": "views-field views-field-title-field"
}).get_text()
grade = tr.find(attrs={
"class": "views-field views-field-field-epso-grade"
}).get_text()
institute = tr.find(attrs={
"class":
"views-field views-field-field-epso-institution-id"
}).get_text()
url = "https://epso.europa.eu" + tr.find(
attrs={
"class": "views-field views-field-title-field"
}).a.get("href")
date_deadline = tr.find(
attrs={
"class": "views-field views-field-field-epso-deadline"
}).get_text()
contract = tr.find(attrs={
"class":
"views-field views-field-field-epso-type-of-contract"
}).get_text()
deadline = data_format.dateFormatFull(
date_deadline.split("-")[0].strip())
# Extract the agency code
try:
inst_code = re.search('\((.*?)\)', institute).groups()[0]
except:
inst_code = institute
check_institute = epso.EPSOinstitution(inst_code)
#print ("inst:" + check_institute)
if check_institute[2] == 1:
continue
# Retrieve the agency's id from eu_institute
inst_id = check_institute[0]
# Retrieve the agency's type from eu_institute
inst_type = check_institute[1]
# Determine the grade
jobType = data_format.typeOfGrade(grade)
# Insert job details in database
epso.persist(inst_id, jobTitle,
str(grade).strip(),
str(institute).strip(), '', deadline,
str(url).strip(), inst_type, jobType)
print(inst_id, jobTitle,
str(grade).strip(),
str(institute).strip(), '', deadline,
str(url).strip(), inst_type, jobType)
page = int(page) + 1
epso_link = epso_link + str(page)
html = urllib.request.urlopen(epso_link)
text = html.read().decode('utf-8')
soup = BeautifulSoup(text, "html.parser")
start = soup.find(attrs={"class": "view-content"})
i = 2
print(
"#========================EPSO SCRAPING COMPLETE================================="
)
def scrapEurojust():
print("#========================= EUROJUST SCRAPING =========================")
# Database connection and agency retrieval
eurojustData = eurojust.returnAgency('EUROJUST')
eurojust_link = eurojustData['link'][0]
eurojust_id = eurojustData['id'][0]
html = urllib.request.urlopen(eurojust_link)
soup = BeautifulSoup(html, "html.parser")
# Find the first ad
start = soup.findAll("table",attrs={"class":"vacancyAnnouncements2"})
# Iterate through the tables
for table in start:
for ad in table.findAll("tr",attrs={"class":"vacancyAnnouncements2Row"}):
title = jobType = deadline = url = jobTitle = None
for piece in ad.findAll("td"):
if (title is None):
title = piece.get_text()
continue
elif (url is None):
url = piece.find('a').get('href')
jobTitle = piece.get_text()
continue
elif (deadline is None):
deadline = piece.get_text()[1:]
deadlineFormatted = data_format.dateFormatFull(str(deadline).replace('/',' '))
continue
else:
pass
print (jobTitle, deadlineFormatted)
jobType = data_format.typeOfGrade(title)
eurojust.persist(int(eurojust_id), str(jobTitle).strip(), '', '', str(title).strip(), deadlineFormatted, str(url).strip(), '', jobType)
for ad in table.findAll("tr",attrs={"class" : "vacancyAnnouncements2AlternatingRow"}):
title = deadline = url = jobTitle = jobType = None
for piece in ad.findAll("td"):
if (title is None):
title = piece.get_text()
continue
elif (url is None):
url = piece.find('a').get('href')
jobTitle = piece.get_text()
continue
elif (deadline is None):
deadline = piece.get_text()[1:]
deadlineFormatted = data_format.dateFormatFull(str(deadline).replace('/', ' '))
continue
else:
pass
print (jobTitle, deadlineFormatted)
jobType = data_format.typeOfPost(title)
# Insert job details in database
eurojust.persist(int(eurojust_id), str(jobTitle).strip(), '', '', str(title).strip(), deadlineFormatted, str(url).strip(), '', jobType)
print("#========================EUROJUST SCRAPING COMPLETE=================================")
def scrapEDA():
print("#========================= EDA SCRAPING =========================")
edaData = eda.returnAgency('EDA')
eda_link = edaData['link'][0]
eda_id = edaData['id'][0]
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36"
headers = { 'User-Agent' : user_agent }
data = ''
data = data.encode('ascii')
req = urllib.request.Request(eda_link,data,headers)
#print(emsa_link)
with urllib.request.urlopen(req) as response:
html = response.read()
soup = BeautifulSoup(html, "html.parser")
# Iterate through the internal groups
for post_type in soup.find_all("h4"):
internal_type = post_type.contents[0].strip()
if internal_type not in ('Temporary Agents','Contractual Agents','Seconded National Experts'):
continue
elif internal_type == 'Temporary Agents':
job_type = 'TA'
elif internal_type == 'Contractual Agents':
job_type = 'CA'
else:
job_type = 'SNE'
print (post_type.contents[0])
internals = post_type.next_element.next_element.next_element.find_all("li")
#try:
# Iterate the URLs for each TA post
for post in internals:
ta_link = eda_link + post.find('a').get("href")
ta_req = urllib.request.Request(ta_link,data,headers)
with urllib.request.urlopen(ta_req) as response:
ta_html = response.read()
ta_soup = BeautifulSoup(ta_html, "html.parser")
#Link
print (ta_link)
#Post
post_title = ta_soup.findAll(attrs={"id":"cphMain_VacNotice_LabPost"})[0].contents[0].strip()
print (post_title)
#Grade
post_grade = ta_soup.findAll(attrs={"id":"cphMain_VacNotice_LabGrade"})[0].contents[0].strip()
print (post_grade)
#Deadline
post_deadline = ta_soup.findAll(attrs={"id":"cphMain_VacNotice_LabPublicationDateEnd"})
print (post_deadline[0].contents[0].strip()+ "\n")
# Convert date
try:
date_object = datetime.strptime(post_deadline[0].contents[0].strip(), '%d %B %Y')
deadline = date_object.date()
#print (deadline)
except:
print ("could not modify " + str(post_deadline))
pass
# Insert job details in database
eda.persist(int(eda_id), str(post_title).strip(), str(post_grade), '', '', deadline, str(ta_link).strip(), '', job_type)
#except:
# pass
print("#========================EDA SCRAPING COMPLETE=================================")
def scrapEPSO():
print("#========================= EPSO SCRAPING =========================")
epsoData = epso.returnAgency('EPSO')
epso_link = epsoData['link'][0]
html = urllib.request.urlopen(epso_link)
text = html.read().decode('utf-8')
soup = BeautifulSoup(text, "html.parser")
#Initiate scrap
start = soup.find(attrs={"class": "view-content"})
page = 0
while (start is not None):
table = start.tbody.findAll("tr")
for tr in table:
# Retrieve job information
print (tr.find(attrs={"class": "views-field views-field-field-epso-locations"}).get_text())
jobTitle = tr.find(attrs={"class": "views-field views-field-title-field"}).get_text()
grade = tr.find(attrs={"class": "views-field views-field-field-epso-grade"}).get_text()
institute = tr.find(attrs={"class": "views-field views-field-field-epso-institution-id"}).get_text()
url = "https://epso.europa.eu"+ tr.find(attrs={"class": "views-field views-field-title-field"}).a.get("href")
date_deadline = tr.find(attrs={"class": "views-field views-field-field-epso-deadline"}).get_text()
contract = tr.find(attrs={"class": "views-field views-field-field-epso-type-of-contract"}).get_text()
deadline = data_format.dateFormatFull(date_deadline.split ("-")[0].strip())
# Extract the agency code
try:
inst_code = re.search('\((.*?)\)', institute).groups()[0]
except:
inst_code = institute
check_institute = epso.EPSOinstitution(inst_code)
#print ("inst:" + check_institute)
if check_institute[2] == 1:
continue
# Retrieve the agency's id from eu_institute
inst_id = check_institute[0]
# Retrieve the agency's type from eu_institute
inst_type = check_institute[1]
# Determine the grade
jobType = data_format.typeOfGrade(grade)
# Insert job details in database
epso.persist(inst_id, jobTitle, str(grade).strip(), str(institute).strip(), '', deadline, str(url).strip(), inst_type, jobType)
print (inst_id, jobTitle, str(grade).strip(), str(institute).strip(), '', deadline, str(url).strip(), inst_type, jobType)
page = int(page) + 1
epso_link = epso_link + str(page)
html = urllib.request.urlopen(epso_link)
text = html.read().decode('utf-8')
soup = BeautifulSoup(text, "html.parser")
start = soup.find(attrs={"class": "view-content"})
i = 2
print("#========================EPSO SCRAPING COMPLETE=================================")
def scrapEUROPOL():
print("#========================= EUROPOL SCRAPING =========================")
europolData = europol.returnAgency('EUROPOL')
europol_link = europolData['link'][0]
europol_id = europolData['id'][0]
html = urllib.request.urlopen(europol_link)
soup = BeautifulSoup(html, "html.parser")
def dateFormatFull (inputDate):
dnotz = None
for form in ['%d %b %Y', '%d %b %y',
'%d %B %Y','%d/%m/%Y','%d.%m.%Y']:
try:
dnotz = datetime.strptime(inputDate, form).date()
return str(dnotz)
except:
continue
if dnotz is None :
print ('Bad Date:',inputDate)
return str(inputDate)
# Find all ads
start = soup.findAll(attrs={"class":re.compile("^views-row views-row-")})
#print ("posts found " + str(len(start)))
# Iterate through the divs
for advert in start:
try:
deadline = advert.find(attrs={"class":"views-field views-field-deadline"}).findAll('span')[1].get_text()
deadlineFormatted = dateFormatFull(deadline)
print ("Deadline:",dateFormatFull(deadline))
print("Contract Type:", advert.find(attrs={"class": "views-field views-field-contract-type"}).find('span').get_text())
jobTitle = advert.find("a").get_text()
print("Title:", jobTitle)
dept = advert.find(attrs={"class": "views-field views-field-department"}).find('span').get_text()
print("Department:", dept)
title = advert.find(attrs={"class": "views-field views-field-reference-number"}).find('span').get_text()
print("Reference Number:", title)
url = "http://www.europol.europa.eu" + advert.find("a").get("href")
print("Link:", url)
except:
continue
if re.search('(AD+\d{1,2}?|AD +\d{1,2}?|TA)',title) is not None:
jobType="AD"
elif re.search('(AST+\d{1,2}?|AST +\d{1,2}?)',title)is not None:
jobType="AST"
elif re.search('(FG+\d|FG+III|FG+IV|Function Groups|CA)',title)is not None:
jobType="CA"
elif re.search('(trainee)',title,re.IGNORECASE)is not None:
jobType="Trainee"
elif re.search('(SNE|Seconded)',title,re.IGNORECASE)is not None:
jobType="SNE"
else:
jobType="Other"
print(int(europol_id), str(jobTitle).strip(), '', str(dept).strip(), str(title).strip(), deadlineFormatted, str(url).strip(), '', jobType)
europol.persist(int(europol_id), str(jobTitle).strip(), '', str(dept).strip(), str(title).strip(), deadlineFormatted,str(url).strip(), '', jobType)
print("#========================EUROPOL SCRAPING COMPLETE=================================")
def call(self):
database.persist()
os._exit(1)
