Last active
August 5, 2022 12:16
-
-
Save necroshine0/321ca44273b6cb04d9673ddb6ed35ddf to your computer and use it in GitHub Desktop.
How to collect students' VK profiles via Python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import vk | |
import json | |
import pandas as pd | |
# Use vk api for data collecting, access token is needed | |
TOKEN = 'yourtoken' | |
vk_api = vk.API(access_token=TOKEN, v='5.131') | |
# find students aged 18-24 with photo from Russia, Moscow | |
# docs: https://dev.vk.com/method/users.search | |
def get_people(age, man=2): | |
return vk_api.users.search(sort=0, hometown='Москва', country=1, city=1, online=0, offset=15, sex=man, | |
count=1000, has_photo=1, fields='education,sex,bdate,city', age_from=age, age_to=age)['items'] | |
people = [] | |
for age in [_ for _ in range(18, 25)]: | |
men = get_people(age) | |
women = get_people(age, man=1) | |
people += (men + women) | |
# Validate | |
edu = [] | |
for p in people: | |
if 'city' in p and 'university' in p and p['university'] > 0: | |
edu += [p] | |
edu[-1]['id'] = 'https://vk.com/id' + str(edu[-1]['id']) | |
df = pd.DataFrame(edu) | |
df['name'] = df.first_name + ' ' + df.last_name | |
df['city'] = 'Москва' | |
# convert birthday (date) to age (number) | |
df['bdate'] = pd.to_datetime(df['bdate'], errors="coerce") | |
df['age'] = (pd.to_datetime('today') - df['bdate']).astype('<m8[Y]').astype(int) | |
df.replace({'sex': {2: 'М', 1: 'Ж'}}, inplace=True) | |
df.drop(columns=['university', 'track_code', 'can_access_closed', 'bdate', 'is_closed', | |
'faculty', 'education_form', 'education_status', 'first_name', 'last_name'], inplace=True) | |
df.to_csv('edu.csv') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment