In [2]:

    

import json


    

In [3]:

    

pairs = sc.textFile('/Users/siauz/Projects/ah/al/pair-0').map(json.loads)
profile = pairs.first()['up1']


    

In [4]:

    

sorted(profile.keys())


    

    
Out[4]:





['age',
 'appRatingByCategory',
 'bio',
 'birthDay',
 'birthMonth',
 'birthYear',
 'birthdateExact',
 'businessTripReady',
 'cert',
 'cgsDone',
 'contactNicks',
 'contacts',
 'coursesAndCertificates',
 'displayContacts',
 'displayDebugInfo',
 'displayLinks',
 'displaySkills',
 'docId',
 'donorDocIds',
 'donorProfileTypes',
 'downloadTime',
 'educations',
 'empty',
 'firstName',
 'gender',
 'industry',
 'interests',
 'jobSeek',
 'languages',
 'lastName',
 'lastPosition',
 'links',
 'loadedAt',
 'location',
 'locations',
 'mainSkills',
 'matchingData',
 'mergerInfos',
 'name',
 'names',
 'nationality',
 'new',
 'nick',
 'nicks',
 'organization',
 'otherInfo',
 'permIds',
 'pictures',
 'portfolio',
 'positions',
 'preferredContact',
 'private',
 'profileTypeRaw',
 'profileWeight',
 'profilesIds',
 'projects',
 'publications',
 'ranking',
 'rating',
 'ratingOnResources',
 'rawGender',
 'rawLocations',
 'rawSkills',
 'rawUrls',
 'readyRelocate',
 'readyRemoteWork',
 'recommendations',
 'relationshipStatus',
 'resourceStars',
 'resumeType',
 'resumeTypesDates',
 'salary',
 'seniorityLevel',
 'short',
 'skillEstimates',
 'skillInfo',
 'sources',
 'specializations',
 'title',
 'transportTime',
 'updatedAt',
 'url',
 'userLinks',
 'userRankEstimates',
 'workHours',
 'workYears']