class TestIgramscraper(unittest.TestCase):
@classmethod
def setUpClass(self):
cwd = os.getcwd()
session_folder = cwd + os.path.sep + 'sessions' + os.path.sep
if username == None or password == None:
self.instagram = Instagram()
else:
self.instagram = Instagram.with_credentials(
username, password, session_folder)
self.instagram.login()
if user_agent != None:
#TODO set user agent
pass
@classmethod
def tearDownClass(self):
pass
def test_get_account_by_username(self):
account = self.instagram.get_account('kevin')
self.assertEqual('kevin', account.username)
self.assertEqual('3', account.identifier)
def test_get_account_by_id(self):
account = self.instagram.get_account_by_id(3)
self.assertEqual('kevin', account.username)
self.assertEqual('3', account.identifier)
def test_get_medias(self):
medias = self.instagram.get_medias('kevin', 80)
self.assertEqual(80, len(medias))
def test_get_hundred_medias(self):
medias = self.instagram.get_medias('kevin', 100)
self.assertEqual(100, len(medias))
def test_get_medias_by_tag(self):
medias = self.instagram.get_medias_by_tag('youneverknow', 20)
self.assertEqual(20, len(medias))
def test_get_medias_by_code(self):
media = self.instagram.get_medias_by_code('BHaRdodBouH')
self.assertEqual('kevin', media.owner.username)
def test_get_media_by_url(self):
media = self.instagram.get_media_by_url(
'https://www.instagram.com/p/BHaRdodBouH')
self.assertEqual('kevin', media.owner.username)
class InstaParser:
"""Получаем информацию из Инстаграма
"""
def __init__(self, set_proxy: bool = False):
config = configparser.ConfigParser()
config.read(settings.CONFIG_INI_PATH)
self.instagram = Instagram()
# self.instagram.with_credentials(
# config['INSTA']['LOGIN'],
# config['INSTA']['PASSWORD'])
# self.instagram.login()
if set_proxy:
# Нужно расширить список адресов, чтобы Инста не блокировала
proxies = {
'http': 'http://123.45.67.8:1087',
'https': 'http://123.45.67.8:1087',
}
self.instagram.set_proxies(proxies)
def get_account_info(self, account: str) -> Dict:
"""Мета-информация об аккаунте
"""
account = self.instagram.get_account(account)
return {
'posts_count': account.media_count,
'followers': account.followed_by_count,
'follows': account.follows_count
}
def get_last_posts(self, account: str) -> List[Dict]:
"""Получаем 100 последних постов аккаунта
"""
try:
medias = self.instagram.get_medias(account, 100)
except:
medias = []
result = []
for media in medias:
if media.caption is not None:
result.append({'id': media.identifier,
'text': media.caption,
'date': datetime.datetime.fromtimestamp(media.created_time),
'likes': media.likes_count,
'url': media.link
})
return result
def get_comments_by_id(self, post_id: str) -> List[Dict]:
"""Получаем последние 100 комментариев к посту по ID
"""
comments = self.instagram.get_media_comments_by_id(post_id, 100)
result = []
if 'comments' in comments:
for comment in comments['comments']:
result.append({
'date': datetime.datetime.fromtimestamp(comment.created_at),
'text': comment.text,
'_is_fake': comment._is_fake,
'id': comment.identifier,
'from_username': comment.owner.username,
'from_full_name': comment.owner.full_name
})
return result
def get_comments_by_code(self, code: str) -> List[Dict]:
"""Получаем последние 100 комментариев к посту по коду
(Работает через раз)
Args:
code (str): Код поста
Returns:
List[Dict]: Список комментариев с мета-информацией
"""
comments = self.instagram.get_media_comments_by_code(code, 100)
result = []
if 'comments' in comments:
for comment in comments['comments']:
result.append({
'date': datetime.datetime.fromtimestamp(comment.created_at),
'text': comment.text,
'_is_fake': comment._is_fake,
'id': comment.identifier,
'username': comment.owner.username,
'from_full_name': comment.owner.full_name
})
return result
def get_post_by_url(self, url: str) -> Dict:
"""Получаем пост по URL
Args:
url (str): Ссылка на пост
Returns:
Dict: Информация о посте
"""
media = self.instagram.get_media_by_url(media_url=url)
return {
'id': media.identifier,
'text': media.caption,
'date': datetime.datetime.fromtimestamp(media.created_time),
'likes': media.likes_count
}
def url2acc(self, url: str) -> str:
"""Извлекает из ссылки на аккаунт имя аккаунта
Args:
url (str): Ссылка на аккаунт. Например: https://www.instagram.com/new_ulyanovsk/
Returns:
str: Аккаунт для применения в методах парсинга: new_ulyanovsk
"""
return url.split('https://www.instagram.com/')[1].split('/')[0]
def url2code(self, url: str) -> str:
"""Получаем код поста из url
Args:
url (str): Ссылка на пост. Например: https://www.instagram.com/p/CHDn3eMMenH
Returns:
str: Код поста: CHDn3eMMenH
"""
return url.split('https://www.instagram.com/p/')[1].split('/')[0]
def get_post_likes(self, code: str) -> int:
"""Получаем количество лайков поста по его коду
Args:
code (str): Код поста
Returns:
int: Количество лайков
"""
return self.instagram.get_media_likes_by_code(code)
class TestIgramscraper(unittest.TestCase):
@classmethod
def setUpClass(self):
cwd = os.getcwd()
session_folder = cwd + os.path.sep + 'sessions' + os.path.sep
if username == None or password == None:
self.instagram = Instagram()
else:
self.instagram = Instagram()
self.instagram.with_credentials(username, password, session_folder)
self.instagram.login()
if user_agent != None:
#TODO set user agent
pass
@classmethod
def tearDownClass(self):
pass
def test_get_account_by_username(self):
account = self.instagram.get_account('kevin')
self.assertEqual('kevin', account.username)
self.assertEqual('3', account.identifier)
def test_get_account_by_id(self):
account = self.instagram.get_account_by_id(3)
self.assertEqual('kevin', account.username)
self.assertEqual('3', account.identifier)
def test_get_medias(self):
medias = self.instagram.get_medias('kevin', 80)
self.assertEqual(80, len(medias))
def test_get_hundred_medias(self):
medias = self.instagram.get_medias('kevin', 100)
self.assertEqual(100, len(medias))
def test_get_medias_by_tag(self):
medias = self.instagram.get_medias_by_tag('youneverknow', 20)
self.assertEqual(20, len(medias))
def test_get_medias_by_code(self):
media = self.instagram.get_medias_by_code('BHaRdodBouH')
self.assertEqual('kevin', media.owner.username)
def test_get_media_by_url(self):
media = self.instagram.get_media_by_url('https://www.instagram.com/p/BHaRdodBouH')
self.assertEqual('kevin', media.owner.username)
def test_get_account_by_id_with_invalid_numeric_id(self):
# sys.maxsize is far larger than the greatest id so far and thus does not represent a valid account.
try:
self.instagram.get_account_by_id(sys.maxsize)
except Exception as e:
self.assertEqual(str(e), 'Failed to fetch account with given id')
def test_get_location_top_medias_by_id(self):
medias = self.instagram.get_current_top_medias_by_tag_name(1)
self.assertEqual(9, len(medias))
def test_get_location_medias_by_id(self):
medias = self.instagram.get_medias_by_location_id(1, 56)
self.assertEqual(56, len(medias))
def test_get_location_by_id(self):
location = self.instagram.get_location_by_id(1)
self.assertEqual('Dog Patch Labs', location.name)
def test_get_id_from_code(self):
code = Media.get_code_from_id('1270593720437182847')
self.assertEqual('BGiDkHAgBF_', code)
code = Media.get_code_from_id('1270593720437182847_3')
self.assertEqual('BGiDkHAgBF_', code)
code = Media.get_code_from_id(1270593720437182847)
self.assertEqual('BGiDkHAgBF_', code)
def test_get_code_from_id(self):
id = Media.get_id_from_code('BGiDkHAgBF_')
self.assertEqual(1270593720437182847, id)
def test_get_media_comments_by_code(self):
comments = self.instagram.get_media_comments_by_code('BR5Njq1gKmB', 40)
#TODO: check why returns less comments
self.assertLessEqual(40, len(comments))
def test_get_username_by_id(self):
username = self.instagram.get_username_by_id(3)
self.assertEqual('kevin', username)
def test_get_medias_by_user_id(self):
medias = self.instagram.get_medias_by_user_id(3)
self.assertEqual(12, len(medias))
from igramscraper.instagram import Instagram
# If account is public you can query Instagram without auth
instagram = Instagram()
# If account is private and you subscribed to it, first login
# instagram.with_credentials('username', 'password', 'cachePath')
# instagram.login()
media = instagram.get_media_by_url('https://www.instagram.com/p/BHaRdodBouH')
print(media)
print(media.owner)
class InstagramHelper:
instagram = None
def __init__(self):
self.instagram = Instagram()
def set_credentials(self, username, password):
self.instagram.with_credentials(username, password)
self.instagram.login()
def get_all_comments(self, url=None, private=False):
if url is None:
return None #NOPE OUT IF URL IS NOT PASSED
all_comment_objs = []
try:
# REMOVE IGSHID
if '?igshid=' in url:
url = str(url).split('?igshid=')[0]
# GET MEDIA ID
media = self.instagram.get_media_by_url(url)
media_id = media.identifier
# GET COMMENTS
comments = self.instagram.get_media_comments_by_id(media_id, 10000)
all_comment_objs = comments['comments']
except Exception as e:
print(e)
pass
return all_comment_objs
def filter_comments(self, comments, filter_string):
valid_comments = []
# filter is assumed to be a comma seperated list of filters
# they can be hashtags as well
# remove inconsistent spaces after commas
filter_string = filter_string.replace(', ', ',')
filters = filter_string.split(',')
for comment in comments:
valid_comment = True
for f in filters:
if str(f).lower() not in str(comment.text).lower():
valid_comment = False
if valid_comment:
valid_comments.append(comment)
return valid_comments
def mention_count_filter(self, comments, required_count=0):
valid_comments = []
for comment in comments:
if str(comment.text).count('@') >= required_count:
valid_comments.append(comment)
return valid_comments
def get_random_comment(self, comments):
return comments[random.randint(0, len(comments) - 1 )]
from igramscraper.instagram import Instagram
import sys
import json
instagram = Instagram()
media = instagram.get_media_by_url(sys.argv[1])
if media.video_standard_resolution_url:
print(media.video_standard_resolution_url)
elif media.image_standard_resolution_url:
print(media.image_standard_resolution_url)
