def media_info_a1(self, media_pk: int, max_id: str = None) -> Media:
"""
Get Media from PK
Parameters
----------
media_pk: int
Unique identifier of the media
max_id: str, optional
Max ID, default value is None
Returns
-------
Media
An object of Media type
"""
media_pk = self.media_pk(media_pk)
shortcode = InstagramIdCodec.encode(media_pk)
"""Use Client.media_info
"""
params = {"max_id": max_id} if max_id else None
data = self.public_a1_request(
"/p/{shortcode!s}/".format(**{"shortcode": shortcode}),
params=params)
if not data.get("shortcode_media"):
raise MediaNotFound(media_pk=media_pk, **data)
return extract_media_gql(data["shortcode_media"])
def media_info_gql(self, media_pk: int) -> Media:
"""
Get Media from PK
Parameters
----------
media_pk: int
Unique identifier of the media
Returns
-------
Media
An object of Media type
"""
media_pk = self.media_pk(media_pk)
shortcode = InstagramIdCodec.encode(media_pk)
"""Use Client.media_info
"""
variables = {
"shortcode": shortcode,
"child_comment_count": 3,
"fetch_comment_count": 40,
"parent_comment_count": 24,
"has_threaded_comments": False,
}
data = self.public_graphql_request(
variables, query_hash="477b65a610463740ccdb83135b2014db")
if not data.get("shortcode_media"):
raise MediaNotFound(media_pk=media_pk, **data)
if data["shortcode_media"]["location"]:
data["shortcode_media"]["location"] = self.location_complete(
extract_location(data["shortcode_media"]["location"])).dict()
return extract_media_gql(data["shortcode_media"])
def hashtag_medias_a1_chunk(
self, name: str, max_amount: int = 27, tab_key: str = "", end_cursor: str = None
) -> Tuple[List[Media], str]:
"""
Get chunk of medias and end_cursor by Public Web API
Parameters
----------
name: str
Name of the hashtag
max_amount: int, optional
Maximum number of media to return, default is 27
tab_key: str, optional
Tab Key, default value is ""
end_cursor: str, optional
End Cursor, default value is None
Returns
-------
Tuple[List[Media], str]
List of objects of Media and end_cursor
"""
unique_set = set()
medias = []
while True:
data = self.public_a1_request(
f"/explore/tags/{name}/",
params={"max_id": end_cursor} if end_cursor else {},
)["hashtag"]
page_info = data["edge_hashtag_to_media"]["page_info"]
end_cursor = page_info["end_cursor"]
edges = data[tab_key]["edges"]
for edge in edges:
if max_amount and len(medias) >= max_amount:
break
# check uniq
media_pk = edge["node"]["id"]
if media_pk in unique_set:
continue
unique_set.add(media_pk)
# check contains hashtag in caption
media = extract_media_gql(edge["node"])
if f"#{name}" not in media.caption_text:
continue
# Enrich media: Full user, usertags and video_url
medias.append(self.media_info_gql(media_pk))
######################################################
# infinity loop in hashtag_medias_top_a1
# https://github.com/adw0rd/instagrapi/issues/52
######################################################
# Mikhail Andreev, [30.12.20 02:17]:
# Instagram always returns the same 9 medias for top
# I think we should return them without a loop
######################################################
# if not page_info["has_next_page"] or not end_cursor:
# break
# if max_amount and len(medias) >= max_amount:
# break
break
return medias, end_cursor
def usertag_medias_gql(self,
user_id: int,
amount: int = 0,
sleep: int = 2) -> List[Media]:
"""
Get medias where a user is tagged (by Public GraphQL API)
Parameters
----------
user_id: int
amount: int, optional
Maximum number of media to return, default is 0 (all medias)
sleep: int, optional
Timeout between pages iterations, default is 2
Returns
-------
List[Media]
A list of objects of Media
"""
amount = int(amount)
user_id = int(user_id)
medias = []
end_cursor = None
variables = {
"id": user_id,
"first": 50 if not amount or amount > 50 else amount,
# These are Instagram restrictions, you can only specify <= 50
}
while True:
if end_cursor:
variables["after"] = end_cursor
data = self.public_graphql_request(
variables, query_hash="be13233562af2d229b008d2976b998b5")
page_info = json_value(data,
"user",
"edge_user_to_photos_of_you",
"page_info",
default={})
edges = json_value(data,
"user",
"edge_user_to_photos_of_you",
"edges",
default=[])
for edge in edges:
medias.append(edge["node"])
end_cursor = page_info.get("end_cursor")
if not page_info.get("has_next_page") or not end_cursor:
break
if amount and len(medias) >= amount:
break
time.sleep(sleep)
if amount:
medias = medias[:amount]
return [extract_media_gql(media) for media in medias]
def user_medias_gql(self,
user_id: int,
amount: int = 50,
sleep: int = 2) -> List[Media]:
"""
Get a user's media by Public Graphql API
Parameters
----------
user_id: int
amount: int, optional
Maximum number of media to return, default is 50
sleep: int, optional
Timeout between pages iterations, default is 2
Returns
-------
List[Media]
A list of objects of Media
"""
amount = int(amount)
user_id = int(user_id)
medias = []
end_cursor = None
variables = {
"id": user_id,
"first": 50 if amount > 50 else
amount, # These are Instagram restrictions, you can only specify <= 50
}
while True:
if end_cursor:
variables["after"] = end_cursor
data = self.public_graphql_request(
variables, query_hash="e7e2f4da4b02303f74f0841279e52d76")
page_info = json_value(data,
"user",
"edge_owner_to_timeline_media",
"page_info",
default={})
edges = json_value(data,
"user",
"edge_owner_to_timeline_media",
"edges",
default=[])
for edge in edges:
medias.append(edge["node"])
end_cursor = page_info.get("end_cursor")
if not page_info.get("has_next_page") or not end_cursor:
break
if len(medias) >= amount:
break
time.sleep(sleep)
return [extract_media_gql(media) for media in medias[:amount]]
def user_medias_paginated_gql(self,
user_id: int,
amount: int = 0,
sleep: int = 2,
end_cursor=None) -> Tuple[List[Media], str]:
"""
Get a page of a user's media by Public Graphql API
Parameters
----------
user_id: int
amount: int, optional
Maximum number of media to return, default is 0 (all medias)
sleep: int, optional
Timeout between pages iterations, default is 2
end_cursor: str, optional
Cursor value to start at, obtained from previous call to this method
Returns
-------
Tuple[List[Media], str]
A tuple containing a list of medias and the next end_cursor value
"""
amount = int(amount)
user_id = int(user_id)
medias = []
variables = {
"id": user_id,
"first": 50 if not amount or amount > 50 else amount,
# These are Instagram restrictions, you can only specify <= 50
}
variables["after"] = end_cursor
data = self.public_graphql_request(
variables, query_hash="e7e2f4da4b02303f74f0841279e52d76")
page_info = json_value(data,
"user",
"edge_owner_to_timeline_media",
"page_info",
default={})
edges = json_value(data,
"user",
"edge_owner_to_timeline_media",
"edges",
default=[])
for edge in edges:
medias.append(edge["node"])
end_cursor = page_info.get("end_cursor")
if amount:
medias = medias[:amount]
return ([extract_media_gql(media) for media in medias], end_cursor)
def hashtag_medias_a1(self,
name: str,
amount: int = 27,
tab_key: str = '') -> List[Media]:
"""
Get medias for a hashtag
Parameters
----------
name: str
Name of the hashtag
amount: int, optional
Maximum number of media to return, default is 27
tab_key: str, optional
Tab Key, default value is ""
Returns
-------
List[Media]
List of objects of Media
"""
unique_set = set()
medias = []
end_cursor = None
while True:
data = self.public_a1_request(
f'/explore/tags/{name}/',
params={"max_id": end_cursor} if end_cursor else {})['hashtag']
page_info = data["edge_hashtag_to_media"]["page_info"]
end_cursor = page_info["end_cursor"]
edges = data[tab_key]["edges"]
for edge in edges:
if amount and len(medias) >= amount:
break
# check uniq
media_pk = edge['node']['id']
if media_pk in unique_set:
continue
unique_set.add(media_pk)
# check contains hashtag in caption
media = extract_media_gql(edge['node'])
if f'#{name}' not in media.caption_text:
continue
# Enrich media: Full user, usertags and video_url
medias.append(self.media_info_gql(media_pk))
######################################################
# infinity loop in hashtag_medias_top_a1
# https://github.com/adw0rd/instagrapi/issues/52
######################################################
# Mikhail Andreev, [30.12.20 02:17]:
# Instagram always returns the same 9 medias for top
# I think we should return them without a loop
######################################################
# if not page_info["has_next_page"] or not end_cursor:
# break
# if amount and len(medias) >= amount:
# break
break
if amount:
medias = medias[:amount]
return medias
