You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
75 lines
2.4 KiB
75 lines
2.4 KiB
import hashlib
|
|
import json
|
|
import random
|
|
import re
|
|
|
|
from requests_futures.sessions import FuturesSession
|
|
|
|
|
|
BASE_URL = 'https://www.instagram.com'
|
|
QUERY_HASH = '42323d64886122307be10013ad2dcc44'
|
|
SHARED_DATA = re.compile(r'window\._sharedData = (\{.*\});</script>')
|
|
|
|
|
|
class Instagram(object):
|
|
def __init__(self, username):
|
|
self.username = username
|
|
shared_data = self._get_shared_data()
|
|
try:
|
|
graphql = shared_data['entry_data']['ProfilePage'][0]['graphql']
|
|
self.user = {k: v for k, v in graphql['user'].items() if not k.startswith('edge')}
|
|
self.rhx_gis = self._get_rhx_gis()
|
|
except (IndexError, KeyError, TypeError):
|
|
self.user = {}
|
|
self.rhx_gis = None
|
|
|
|
def _get_rhx_gis(self):
|
|
s = json.dumps(dict(id=random.randint(10000000, 99999999)))
|
|
return hashlib.md5(s.encode('UTF-8')).hexdigest()
|
|
|
|
def _get_shared_data(self):
|
|
session = FuturesSession()
|
|
r = session.get('{0}/{1}'.format(BASE_URL, self.username)).result()
|
|
if not r.ok:
|
|
return None
|
|
m = SHARED_DATA.search(r.text)
|
|
if m:
|
|
return json.loads(m.group(1))
|
|
return None
|
|
|
|
def fetch_media(self):
|
|
session = FuturesSession()
|
|
def get_media(count, cursor):
|
|
variables = json.dumps(dict(
|
|
id=self.user.get('id'),
|
|
first=count,
|
|
after=cursor))
|
|
gis = '{0}:{1}'.format(self.rhx_gis, variables)
|
|
gis = hashlib.md5(gis.encode('UTF-8')).hexdigest()
|
|
url = '{0}/graphql/query'.format(BASE_URL)
|
|
params = dict(
|
|
query_hash=QUERY_HASH,
|
|
variables=variables)
|
|
return session.get(url, params=params, headers={'X-Instagram-GIS': gis})
|
|
result = []
|
|
count = 50
|
|
cursor = ''
|
|
while True:
|
|
request = get_media(count, cursor)
|
|
r = request.result()
|
|
if not r.ok:
|
|
return []
|
|
data = r.json()
|
|
try:
|
|
data = data['data']['user']['edge_owner_to_timeline_media']
|
|
except KeyError:
|
|
return []
|
|
for edge in data.get('edges', []):
|
|
node = edge.get('node', {})
|
|
node['owner'].update(self.user)
|
|
result.append(node)
|
|
cursor = data['page_info']['end_cursor']
|
|
if not cursor:
|
|
break
|
|
return result
|