gistfile1.txt

#! /usr/bin/env python
from ats.one_click_applier import ATSApplierInput
from ats.taleo.applier_type_test import TaleoApplier
from collections import Counter
from postings.selenium_visitor import PostingSeleniumVisitor
from util.orator.job_scout import JobScout
from util.proxies import setup_phantom
from util.database import setup_cursor, execute_query
from util.aws import INTERNAL_BUCKET, S3Downloader


job_scout = JobScout(user_id=0, posting_id=0,
                        context={'application_user_info': {}})
applier_input = ATSApplierInput(job_scout, "resume.txt")


def load_visitor():
    service_args = ['--proxy-type=http',
                    '--webdriver-loglevel=ERROR']
    posting_driver = setup_phantom(service_args)
    visitor = PostingSeleniumVisitor(posting_driver)
    return visitor


def check_applier_type(visitor, taleo_url):
    visitor.get_posting_info(taleo_url)
    applier_type = TaleoApplier.factory(visitor, applier_input)
    return applier_type


if __name__ == '__main__':
    db_cursor = setup_cursor()
    query = "select id, cache_url, source_url from postings where source_url like '%taleo%'"
    query += " and posted_at > '2016-12-15'::date and not description like '%##%' and cache_url is not null;"
    query_results = [x for x in execute_query(db_cursor, query)]
    visitor = load_visitor()
    results = dict()
    local_server_prefix = 'http://127.0.0.1:8080/'
    for entry in query_results:
        try:
            s3_path = entry['cache_url']
            dler = S3Downloader(INTERNAL_BUCKET, s3_path[s3_path.find(INTERNAL_BUCKET) +
                                len(INTERNAL_BUCKET) + 1:])
            # expects http-server running at root as the temp files are placed relative to root
            temp_file_path = dler.__enter__()
            results[entry['id']] = check_applier_type(visitor,
                local_server_prefix + temp_file_path)
            dler.__exit__('', '', '')  # empty strings are for unused args in method.
            print("Finished applier check for " + entry['source_url'] + ': ' + results[entry['id']])
        except:
            print('Skipping ' + entry['id'] + 'due to error')
    print("Applier type counts:")
    print(Counter(results.values()))
    print(results)
    visitor.close()

# edits to applier file:
def factory(visitor, ats_applier_input):
        simple_submit_xpath = "//input[@value='Apply for this Position']"
        simple_submit_elems = visitor.driver.find_elements_by_xpath(simple_submit_xpath)

        one_page_submit_with_creds_xpath = "//span[@class='head1' and text()='Submit Application']"
        one_page_submit_with_creds_elems = visitor.driver.find_elements_by_xpath(one_page_submit_with_creds_xpath)

        if simple_submit_elems:
            return "Simple"
        elif one_page_submit_with_creds_elems:
            return "One_page"
        else:
            return "Pipeline"