def scrape(query, numresults):
scraper = LinkedinScraper(
chrome_executable_path=None, # Custom Chrome executable path (e.g. /foo/bar/bin/chromedriver)
chrome_options=None, # Custom Chrome options here
headless=False, # Overrides headless mode only if chrome_options is None
max_workers=1, # How many threads will be spawned to run queries concurrently (one Chrome driver for each thread)
slow_mo=1, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
# Add event listeners
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
queries = [
Query(
query=query,
options=QueryOptions(
locations=['Montreal'],
optimize=True, # Blocks requests for resources like images and stylesheet
limit=numresults # Limit the number of jobs to scrape
)
),
# Query(
# query='database',
# options=QueryOptions(
# locations=['United States'],
# optimize=False,
# limit=5,
# filters=QueryFilters(
# # company_jobs_url='https://www.linkedin.com/jobs/search/?geoId=101174742&keywords=amazon&location=Canada', # Filter by companies
# relevance=RelevanceFilters.RECENT,
# time=TimeFilters.MONTH,
# type=[TypeFilters.FULL_TIME, TypeFilters.INTERNSHIP],
# experience=None,
# )
# )
# ),
]
scraper.run(queries)
global df
dictTemp = {"JobID": [data.job_id] , "Company": [data.company],"Title" : [data.title], "Place": [data.place],"Date": [data.date],"SeniorityLevel": [data.seniority_level],"JobFunction": [data.job_function],"EmployementType": [data.employment_type],"Industries": [data.industries],"description":[data.description]}
dfTemp = pd.DataFrame(dictTemp)
df = df.append(dfTemp,ignore_index = True)
def on_error(error):
print('[ON_ERROR]', error)
def on_end():
print('[ON_END]')
scraper = LinkedinScraper(
chrome_executable_path='C:\chromedriver_win32\chromedriver.exe', # Custom Chrome executable path (e.g. /foo/bar/bin/chromedriver)
chrome_options=None, # Custom Chrome options here
headless=False, # Overrides headless mode only if chrome_options is None
max_workers=1, # How many threads will be spawned to run queries concurrently (one Chrome driver for each thread)
slow_mo=1.4, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
# Add event listeners
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
queries = [
Query(
query='Data Engineer',
options=QueryOptions(
locations=['indonesia','vietnam ','china','singapore','korea selatan','japan','Hong Kong SAR','taiwan'],
for counter in range(2):
if counter == 0:
for search in searches:
title = []
company = []
date = []
link = []
industry = []
occupation = []
jobType = []
scraper = LinkedinScraper(
chrome_options=
None, # You can pass your custom Chrome options here
max_workers=
1, # How many threads will be spawn to run queries concurrently (one Chrome driver for each thread)
slow_mo=
1.2, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
# Add event listeners
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
queries = [
Query(options=QueryOptions(
optimize=
True, # Blocks requests for resources like images and stylesheet
limit=0 # Limit the number of jobs to scrape
)),
def test_run():
# Change other logger levels
logging.getLogger('urllib3').setLevel(logging.WARN)
logging.getLogger('selenium').setLevel(logging.WARN)
scraper = LinkedinScraper(
chrome_executable_path=None,
chrome_options=None,
headless=True,
max_workers=1,
slow_mo=1,
)
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.INVALID_SESSION, on_invalid_session)
scraper.on(Events.END, on_end)
queries = [
Query(),
Query(query='c#',
options=QueryOptions(
locations=['Finland'],
optimize=False,
limit=33,
filters=QueryFilters(
time=TimeFilters.WEEK,
experience=ExperienceLevelFilters.MID_SENIOR,
))),
Query(
query='Engineer',
options=QueryOptions(
locations=['United States'],
optimize=False,
limit=27,
filters=QueryFilters(
company_jobs_url=
'https://www.linkedin.com/jobs/search/?f_C=1441%2C17876832%2C791962%2C2374003%2C18950635%2C16140%2C10440912&geoId=92000000',
time=TimeFilters.MONTH,
type=[
TypeFilters.FULL_TIME, TypeFilters.INTERNSHIP,
TypeFilters.CONTRACT
]))),
]
scraper.run(
queries=queries,
# Global options
options=QueryOptions(
locations=['United Kingdom'],
limit=10,
optimize=False,
))
def scrapeLinkedinJobs(industries):
scraper = LinkedinScraper(
# chrome_executable_path='D:/chromedriver.exe', # Custom Chrome executable path (e.g. /foo/bar/bin/chromedriver)
chrome_executable_path=
'C:/Users/iyeng/Desktop/NTU/NTU Sem 4/CZ2006/JobsUpply/JobsUpply/chromedriver.exe',
chrome_options=None, # Custom Chrome options here
headless=True, # Overrides headless mode only if chrome_options is None
max_workers=len(
industries
), # How many threads will be spawned to run queries concurrently (one Chrome driver for each thread)
slow_mo=
2, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
queries = []
for i in range(len(industries)):
paramQ = Query(
query=industries[i],
options=QueryOptions(
locations=['Singapore'],
optimize=True,
limit=6,
filters=QueryFilters(
company_jobs_url=None, # Filter by companies
relevance=RelevanceFilters.RECENT,
time=TimeFilters.MONTH,
type=[TypeFilters.FULL_TIME],
experience=None,
)))
queries.append(paramQ)
JobList = {}
def on_data(data: EventData):
jobData = {}
jobData["title"] = data.title
jobData["company"] = data.company
jobData["place"] = data.place
jobData["description"] = data.description
jobData["linkedinUrl"] = data.link
jobData["descriptionHTML"] = data.description_html
jobData["employmentType"] = data.employment_type
jobData["applyUrl"] = data.apply_link
jobData["date"] = data.date
jobData["seniority"] = data.seniority_level
jobData["jobFunction"] = data.job_function
jobData["industries"] = data.industries
jobData["skills"] = json.loads(
extract_skills_from_document(data.description))
if data.query not in JobList.keys():
JobList[data.query] = []
JobList[data.query].append(jobData)
else:
JobList[data.query].append(jobData)
del data
del jobData
def on_error(error):
print('[ON_ERROR]', error)
def on_end():
print('[ON_END]')
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
scraper.run(queries)
JobList = [{"queryText": q, "jobList": JobList[q]} for q in JobList.keys()]
return JobList
def on_data(data: EventData):
print('[ON_DATA]', data.title, data.company, data.date, data.link, len(data.description))
def on_error(error):
print('[ON_ERROR]', error)
def on_end():
print('[ON_END]')
scraper = LinkedinScraper(
chrome_executable_path= None,
chrome_options=None, # Custom Chrome options here
headless=True, # Overrides headless mode only if chrome_options is None
max_workers=1,
slow_mo=1, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
# Add event listeners
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
queries = [
Query(
query='Data',
options=QueryOptions(
locations=['Belgium'],
optimize=True,
def linkedinsc():
with open('C:/Projects/itjobseeker/public/jsondata/linkedin.json',
'r') as readfile:
try:
jsondata = json.load(readfile)
stored_links = []
for single_data in jsondata:
stored_links.append(single_data['Page_URL'])
except:
jsondata = []
stored_links = []
# Change root logger level (default is WARN)
logging.basicConfig(level=logging.INFO)
def on_data(data: EventData):
# print('[ON_DATA]', data.title, data.company, data.date, data.link,data.seniority_level,data.employment_type)
link = data.link
link = link.split('?', 1)[0]
if link not in stored_links:
stored_links.append(link)
print("NEW JOB FOUND !!!", link)
source = requests.get(data.link).text
soup = BeautifulSoup(source, 'lxml')
desct = soup.find('main', class_='main').get_text(strip=True)
jsondata.append({
'name': data.title,
'company': data.company,
'address': data.place,
'deadline': data.date,
'time': data.employment_type,
'Page_URL': link,
'desct': desct,
'websitename': 'np.linkedin.com'
})
def on_error(error):
print('[ON_ERROR]', error)
def on_end():
print('[ON_END]')
scraper = LinkedinScraper(
chrome_options=None, # You can pass your custom Chrome options here
headless=True, # Overrides headless mode only if chrome_options is None
max_workers=1,
# How many threads will be spawned to run queries concurrently (one Chrome driver for each thread)
slow_mo=
1.5, # Slow down the scraper to avoid 'Too many requests (429)' errors
)
# Add event listeners
scraper.on(Events.DATA, on_data)
scraper.on(Events.ERROR, on_error)
scraper.on(Events.END, on_end)
queries = [
# Query(
# options=QueryOptions(
# optimize=True, # Blocks requests for resources like images and stylesheet
# limit=50 # Limit the number of jobs to scrape
# )
# ),
Query(
query='it',
options=QueryOptions(
locations=['Nepal'],
optimize=True,
limit=70,
# filters=QueryFilters(
# company_jobs_url='https://www.linkedin.com/jobs/search/?f_C=1441%2C17876832%2C791962%2C2374003%2C18950635%2C16140%2C10440912&geoId=92000000', # Filter by companies
# relevance=RelevanceFilters.RECENT,
# time=TimeFilters.MONTH,
# type=[TypeFilters.FULL_TIME, TypeFilters.INTERNSHIP],
# experience=None,
# )
))
]
scraper.run(queries)
with open('C:/Projects/itjobseeker/public/jsondata/linkedin.json',
'w') as outfile:
json.dump(jsondata, outfile)
print("linkedin done")
