Exemple #1
0
#!/usr/bin/python3

import datetime
import config, people, twitter_api

token = config.load_token('/vagrant/token/twitter.json')

users = people.load('./people.json.pretty')

today = datetime.date.today()

i = 0
for user_id, user in users.items():
    i += 1
    print(i)

    u = twitter_api.user(token, user_id)
    if u is None:
        continue

    if 'since_id' not in user['twitter']:
        user['twitter']['since_id'] = -1
    since_id = user['twitter']['since_id']

    ids = twitter_api.user_tweets_id(token, user_id, since_id)

    if '_activity' not in user['twitter']:
        user['twitter']['_activity'] = {}

    activity = {
        'statuses_count': u['statuses_count'],
Exemple #2
0
#!/usr/bin/python3

import re
import people

users = people.load('./people.json')

for user_id, user in users.items():
  if 'entities' in user['twitter']:
    entities = user['twitter']['entities']
    urls = []
    if 'description' in entities:
      urls.extend(entities['description']['urls'])
    if 'url' in entities:
      urls.extend(entities['url']['urls'])
    for url in urls:
      if 'expanded_url' in url and url['expanded_url'] is not None:
        match = re.match('^.*youtube\.com/watch\?v=.*$', url['expanded_url'])
        if not match:
          match = re.match('^.*youtube\.com/(.*/)*(.*)$', url['expanded_url'])
          if match:
            user['youtube'] = {'id':match.group(2)}

people.save(users, './people.json')
Exemple #3
0
#!/usr/bin/python3

import datetime
today = str(datetime.date.today())

import people
persons = people.load('/vagrant/data/people.json')

import json, requests
from pyquery import PyQuery

for twitter_id, person in persons.items():
  if 'fitbit' not in person:
    continue
  fitbit = person['fitbit']
  if 'url' not in fitbit:
    print('[WARN][' + twitter_id + '] fitbit url is missing')
    continue
  url = fitbit['url']

  r = requests.get(url)

  pq = PyQuery(r.text)

  height = pq('li.user-stat.height')
  location = pq('li.user-stat.location')
  joined = pq('li.user-stat.location')

  aboutme = pq('div.content.firstContent')

  lifetime = pq('div.tabsData.lifetime.cached')
Exemple #4
0
#!/usr/bin/python3

import jellyfish, json, os, re

import people
from url import expand

# work dir
work_dir = os.environ['WORKDIR']
twitter_dir = os.environ['TWITTERDIR']

# load people
people_path = work_dir + '/data/people.json'
persons = people.load(people_path)

# load tweets
tweets_path = twitter_dir + '/3data/url_facebook.json'
with open(tweets_path, 'r') as tweets_file:
    tweets = json.load(tweets_file)

# for each tweet
i = 0
for tweet in tweets['tweets']:
    i += 1

    user = tweet['user']
    tw_name = user['name']
    tw_username = user['screen_name']
    urls = tweet['entities']['urls']

    # for each url
Exemple #5
0
#!/usr/bin/python3

import datetime
today = str(datetime.date.today())

import people
persons = people.load('/vagrant/data/people.json.pretty')

import json, requests
from pyquery import PyQuery

for twitter_id, person in persons.items():
    if 'linkedin' not in person:
        continue
    linkedin = person['linkedin']
    if 'url' not in linkedin:
        print('[WARN][' + twitter_id + '] linkedin url is missing')
        continue
    url = linkedin['url']

    url = 'https://pinterest.com/larryconlin'

    r = requests.get(url)

    with open('/tmp/index.html', 'w') as file:
        file.write(r.text)

    pq = PyQuery(r.text)

    div = pq('div.profile-picture')
    print(div.text())