90 lines
6.7 KiB
Python
90 lines
6.7 KiB
Python
import requests
|
|
from math import ceil
|
|
from csv import DictWriter
|
|
from time import sleep
|
|
|
|
def search_jst_id(csv_file):
|
|
total_pages = 2
|
|
current_page = 1
|
|
url = 'https://xapi.supercharge-srp.co/job-search/graphql?country=id&isSmartSearch=true'
|
|
headers = {
|
|
'Accept': '*/*',
|
|
'Accept-Encoding': 'gzip, deflate, br',
|
|
'Accept-Language': 'en-US,en;q=0.9',
|
|
'Content-Length': '3408',
|
|
'Content-Type': 'application/json',
|
|
'Origin': 'https://www.jobstreet.com.id',
|
|
'Referer': 'https://www.jobstreet.com.id/',
|
|
'Sec-Ch-Ua': '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
|
|
'Sec-Ch-Ua-Mobile': '?0',
|
|
'Sec-Ch-Ua-Platform': '"Windows"',
|
|
'Sec-Fetch-Dest': 'empty',
|
|
'Sec-Fetch-Mode': 'cors',
|
|
'Sec-Fetch-Site': 'cross-site',
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36'
|
|
}
|
|
query = "query getJobs($country: String, $locale: String, $keyword: String, $createdAt: String, $jobFunctions: [Int], $categories: [String], $locations: [Int], $careerLevels: [Int], $minSalary: Int, $maxSalary: Int, $salaryType: Int, $candidateSalary: Int, $candidateSalaryCurrency: String, $datePosted: Int, $jobTypes: [Int], $workTypes: [String], $industries: [Int], $page: Int, $pageSize: Int, $companyId: String, $advertiserId: String, $userAgent: String, $accNums: Int, $subAccount: Int, $minEdu: Int, $maxEdu: Int, $edus: [Int], $minExp: Int, $maxExp: Int, $seo: String, $searchFields: String, $candidateId: ID, $isDesktop: Boolean, $isCompanySearch: Boolean, $sort: String, $sVi: String, $duplicates: String, $flight: String, $solVisitorId: String) {\n jobs(\n country: $country\n locale: $locale\n keyword: $keyword\n createdAt: $createdAt\n jobFunctions: $jobFunctions\n categories: $categories\n locations: $locations\n careerLevels: $careerLevels\n minSalary: $minSalary\n maxSalary: $maxSalary\n salaryType: $salaryType\n candidateSalary: $candidateSalary\n candidateSalaryCurrency: $candidateSalaryCurrency\n datePosted: $datePosted\n jobTypes: $jobTypes\n workTypes: $workTypes\n industries: $industries\n page: $page\n pageSize: $pageSize\n companyId: $companyId\n advertiserId: $advertiserId\n userAgent: $userAgent\n accNums: $accNums\n subAccount: $subAccount\n minEdu: $minEdu\n edus: $edus\n maxEdu: $maxEdu\n minExp: $minExp\n maxExp: $maxExp\n seo: $seo\n searchFields: $searchFields\n candidateId: $candidateId\n isDesktop: $isDesktop\n isCompanySearch: $isCompanySearch\n sort: $sort\n sVi: $sVi\n duplicates: $duplicates\n flight: $flight\n solVisitorId: $solVisitorId\n ) {\n total\n totalJobs\n relatedSearchKeywords {\n keywords\n type\n totalJobs\n }\n solMetadata\n suggestedEmployer {\n name\n totalJobs\n }\n queryParameters {\n key\n searchFields\n pageSize\n }\n experiments {\n flight\n }\n jobs {\n id\n adType\n sourceCountryCode\n isStandout\n companyMeta {\n id\n advertiserId\n isPrivate\n name\n logoUrl\n slug\n }\n jobTitle\n jobUrl\n jobTitleSlug\n description\n employmentTypes {\n code\n name\n }\n sellingPoints\n locations {\n code\n name\n slug\n children {\n code\n name\n slug\n }\n }\n categories {\n code\n name\n children {\n code\n name\n }\n }\n postingDuration\n postedAt\n salaryRange {\n currency\n max\n min\n period\n term\n }\n salaryVisible\n bannerUrl\n isClassified\n solMetadata\n }\n }\n}\n"
|
|
while current_page <= total_pages:
|
|
sleep(1)
|
|
variables = {"keyword":"",
|
|
"jobFunctions":[],
|
|
"locations":[],
|
|
"salaryType":1,
|
|
"jobTypes":[],
|
|
"createdAt":None,
|
|
"careerLevels":[],
|
|
"page": current_page,
|
|
"country":"id",
|
|
"sVi":"",
|
|
"solVisitorId":"7d3f7e5c-471e-411d-8a82-d8d29a303653",
|
|
"categories":[],"workTypes":[],
|
|
"userAgent":"Mozilla/5.0%20(Windows%20NT%2010.0;%20Win64;%20x64)%20AppleWebKit/537.36%20(KHTML,%20like%20Gecko)%20Chrome/118.0.0.0%20Safari/537.36",
|
|
"industries":[],
|
|
"locale":"en"}
|
|
data = {
|
|
'query': query,
|
|
'variables': variables
|
|
}
|
|
error_count = 0
|
|
try:
|
|
response = requests.post(url, json=data, headers=headers, timeout=20)
|
|
if response.status_code == 200:
|
|
result = response.json()
|
|
# print(result['data']['jobs']['totalJobs'])
|
|
# print(type(result['data']['jobs']['totalJobs']))
|
|
# print(result['data']['jobs']['totalJobs']/30)
|
|
# print(result['data']['jobs']['jobs'])
|
|
print('total pages', ceil(result['data']['jobs']['totalJobs']/30))
|
|
total_pages = ceil(result['data']['jobs']['totalJobs']/30)
|
|
if len(result['data']['jobs']['jobs']) > 0 :
|
|
column = ['Company_Name'] + list(result['data']['jobs']['jobs'][0].keys())[:6]
|
|
# print("writing to file")
|
|
with open(csv_file, 'a+', newline='', encoding='utf-8') as csvfile:
|
|
writer = DictWriter(csvfile, fieldnames=column, extrasaction='ignore')
|
|
if csvfile.tell() == 0:
|
|
writer.writeheader()
|
|
# print("writing each array")
|
|
for a_job in result['data']['jobs']['jobs']:
|
|
a_job['Company_Name'] = a_job['companyMeta']['name']
|
|
writer.writerow(a_job)
|
|
|
|
current_page += 1
|
|
# total_pages -=1
|
|
print(f"scraping page {current_page} of {total_pages}")
|
|
else:
|
|
|
|
print(f"Request failed with status code {response.status_code}: {response.text}")
|
|
error_count +=1
|
|
if error_count > 3:
|
|
current_page +=1
|
|
# total_pages -=1
|
|
except Exception as malayError:
|
|
print(malayError)
|
|
error_count+=1
|
|
if error_count > 3:
|
|
current_page +=1
|
|
# total_pages -=1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
search_jst_id("testdata_jst_id.csv") |