def test_pr_122(self):
"""
Feature implemented by @susundberg.
Set the access time and modification time of a downloaded media
according to its IG date.
"""
looter = ProfileLooter('franz_ferdinand',
template='{code}', session=self.session)
info = looter.get_post_info('BY77tSfBnRm')
# Test download_post
post_looter = PostLooter('BY77tSfBnRm',
session=self.session, template='{code}')
post_looter.download(self.destfs)
stat = self.destfs.getdetails('BY77tSfBnRm.jpg')
self.assertEqual(stat.raw["details"]["accessed"], info['taken_at_timestamp'])
self.assertEqual(stat.raw["details"]["modified"], info['taken_at_timestamp'])
# Test download_pictures
pic = next(m for m in looter.medias() if not m['is_video'])
looter.download_pictures(self.destfs, media_count=1)
stat = self.destfs.getdetails('{}.jpg'.format(pic['shortcode']))
self.assertEqual(stat.raw["details"]["accessed"], pic['taken_at_timestamp'])
self.assertEqual(stat.raw["details"]["modified"], pic['taken_at_timestamp'])
# Test download_videos
vid = next(m for m in looter.medias() if m['is_video'])
looter.download_videos(self.destfs, media_count=1)
stat = self.destfs.getdetails('{}.mp4'.format(vid['shortcode']))
self.assertEqual(stat.raw["details"]["accessed"], vid['taken_at_timestamp'])
self.assertEqual(stat.raw["details"]["modified"], vid['taken_at_timestamp'])
def send_text(message):
log(strftime("%Y-%m-%d %H:%M:%S", gmtime()), message)
if 'instagram.com/p/' in message.text:
path = message.text
looter = PostLooter(path)
if looter.info['__typename'] == 'GraphImage':
picture_id = looter.info['id']
looter.download('./pictures/')
bot.send_photo(message.chat.id,
open('./pictures/{}.jpg'.format(picture_id), 'rb'),
caption='🤖 Downloaded with @instsave_bot')
elif looter.info['__typename'] == 'GraphVideo':
video_id = looter.info['id']
looter.download_videos('./videos/')
bot.send_video(message.chat.id,
open('./videos/{}.mp4'.format(video_id), 'rb'),
caption='🤖 Downloaded with @instsave_bot')
elif looter.info['__typename'] == 'GraphSidecar':
bot.send_message(
message.chat.id,
'Sorry, I can\'t send you post with more than 1 photo\n\nPlease try again'
)
elif 'private' in message.text:
bot.send_message(436264579, message.text[7:])
else:
bot.send_message(
message.chat.id,
'Please, send link or username\n\nNeed more help?\nJust tap: /help'
)
def instagram_p(url):
looter = PostLooter(url)
# Скачивание
picture_id = looter.info['id']
looter.download('./pictures/')
file = open('./pictures/{}.jpg'.format(picture_id), 'rb')
return file
def test_issue_094(self):
"""Thanks to @jeanmarctst for raising this issue.
Make sure caption is properly extracted from images downloaded
from a post code and written to the metadata.
"""
looter = PostLooter("BY77tSfBnRm",
add_metadata=True, template='{code}', session=self.session)
looter.download(self.destfs)
metadata = piexif.load(self.destfs.getbytes("BY77tSfBnRm.jpg"), True)
self.assertTrue(metadata['Exif']['UserComment'])
def test_pr_122_download_post(self):
"""Feature implemented by @susundberg.
Set the access time and modification time of a downloaded media
according to its IG date.
"""
code = 'BY77tSfBnRm'
post_looter = PostLooter(code, session=self.session, template='{code}')
info = post_looter.get_post_info(code)
post_looter.download(self.destfs)
stat = self.destfs.getdetails('{}.jpg'.format(code))
self.assertEqual(stat.raw["details"]["accessed"], info['taken_at_timestamp'])
self.assertEqual(stat.raw["details"]["modified"], info['taken_at_timestamp'])
def test_issue_039(self):
"""
Feature request by @verafide
Checks that all pictures are downloaded from posts
with more than one picture.
"""
looter = PostLooter("BRHecUuFhPl", session=self.session)
looter.download(self.destfs)
self.assertEqual(
set(self.destfs.listdir("/")), {
"1461270165803344956.jpg",
"1461270167497776767.jpg",
"1461270174435133336.jpg",
"1461270172581471925.jpg",
"1461270181565655668.jpg",
})
def test_issue_042(self):
"""
Thanks to @MohamedIM for reporting this bug.
Checks that a multipost is successfully downloaded from
the CLI `post` option.
"""
looter = PostLooter('BRW-j_dBI6F',
get_videos=True,
session=self.session)
looter.download(self.destfs)
self.assertEqual(
set(self.destfs.listdir("/")), {
'1465633492745668095.mp4',
'1465633517836005761.mp4',
'1465633541559037966.mp4',
'1465633561523918792.mp4',
})
def application(url, path):
looter = PostLooter(url)
var = looter.download(f"media/{path}")
return var
def scrape_post_from_link(given_link): # scrape post from a given link
looter = PostLooter(given_link)
post_list = []
for post_info in looter.medias():
post_dict = {}
comment_users = []
comment_texts = []
comment_users_verified = []
comment_texts_processed = []
for i in post_info['edge_media_to_parent_comment']['edges']:
comment_users += [i['node']['owner']['username']]
comment_texts += [i['node']['text']]
comment_texts_processed += [process_text(i['node']['text'])]
comment_users_verified += [i['node']['owner']['is_verified']]
try:
caption = post_info['edge_media_to_caption']['edges'][0]['node'][
'text']
except Exception:
caption = ""
if caption:
post_dict['hashtags_cap'] = re.findall(r"#(\w+)", caption)
post_dict['mentions_cap'] = re.findall(r"@(\w+)", caption)
else:
post_dict['hashtags_cap'] = []
post_dict['mentions_cap'] = []
post_dict['shortcode'] = post_info['shortcode']
post_dict['photo_url'] = post_info['display_url']
post_dict['comment_users'] = comment_users
post_dict['comment_texts'] = comment_texts
post_dict['comment_users_verified'] = comment_users_verified
post_dict['comment_texts_processed'] = comment_texts_processed
post_dict['caption'] = caption
post_dict['post_url'] = _baseurl + str(post_info['shortcode'])
post_dict['post_id'] = post_info['id']
post_dict['user_name'] = post_info['owner']['username']
post_dict['user_id'] = post_info['owner']['id']
post_dict['user_full_name'] = post_info['owner']['full_name']
post_dict['user_verified'] = post_info['owner']['is_verified']
post_dict['user_private'] = post_info['owner']['is_private']
post_dict['user_profile_pic_url'] = post_info['owner'][
'profile_pic_url']
post_dict['user_post_count'] = post_info['owner'][
'edge_owner_to_timeline_media']['count']
post_dict['is_ad'] = post_info['is_ad']
post_dict['is_video'] = post_info['is_video']
post_dict['location'] = post_info['location']
post_dict['timestamp'] = post_info['taken_at_timestamp']
post_dict['datetime'] = datetime.fromtimestamp(
post_info['taken_at_timestamp'])
post_dict['comments_disabled'] = post_info['comments_disabled']
post_dict['likes'] = post_info['edge_media_preview_like']['count']
post_dict['comments'] = post_info['edge_media_to_parent_comment'][
'count']
tagged_usernames = []
tagged_user_full_name = []
tagged_user_verified = []
for i in post_info['edge_media_to_tagged_user']['edges']:
tagged_usernames += [i['node']['user']['username']]
tagged_user_full_name += [i['node']['user']['full_name']]
tagged_user_verified += [i['node']['user']['is_verified']]
post_dict['tagged_usernames'] = tagged_usernames
post_dict['tagged_user_full_name'] = tagged_user_full_name
post_dict['tagged_user_verified'] = tagged_user_verified
try:
ploot = PostLooter(post_dict['post_url'])
ploot.download('instaLooter_images/temp/')
img = cv2.imread('instaLooter_images/temp/' + post_info['id'] +
".jpg")
text = pytesseract.image_to_string(img)
post_dict['image_text'] = text
post_dict['hashtags_img'] = re.findall(r"#(\w+)", text)
post_dict['mentions_img'] = re.findall(r"@(\w+)", text)
text = process_text(text)
post_dict['image_text_processed'] = text
except Exception as e:
post_dict['image_text'] = ""
post_dict['hashtags_img'] = ""
post_dict['mentions_img'] = ""
post_dict['image_text_processed'] = ""
post_list += [post_dict]
return post_list
