Alex Benusov
Newbie
- Sep 14, 2016
- 3
- 0
Hope it will be useful for someone.
Instagram Tag Explorer for diggernaut.com
Instagram auto-follower. Follows all followers of given user. Requires instagram account. For diggernaut.com service.
Script to scrape instagram, grabs all user feed data including all followers and follows (requires instagram account). For diggernaut.com service.
Script for instagram scrape, can be used to get public information from user feed (no login info required). For diggernaut.com service
Instagram Tag Explorer for diggernaut.com
Code:
---
config:
agent: Firefox
iterator:
- type: csv
name: tag
value: scraping
do:
- walk:
to: https://www.instagram.com/explore/tags/<%tag%>/
do:
- find:
path: body
do:
- register_set: https://www.instagram.com/p
- variable_set: baseurl
- parse:
filter: window\._sharedData\s+\=\s+([^\n]+);\n
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- find:
path: media>page_info>start_cursor
do:
- parse
- variable_set: cursor
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_hashtag(<%tag%>) { media.after("", 100) {
count,
nodes {
caption,
code,
comments {
count
},
comments_disabled,
date,
dimensions {
height,
width
},
display_src,
id,
is_video,
likes {
viewer_has_liked,
count,
nodes {
user {
id,
username,
profile_pic_url
}
}
},
owner {
id,
username,
full_name,
biography,
external_url,
external_url_linkshimmed,
requested_by_viewer,
has_requested_viewer,
followed_by_viewer,
follows_viewer,
blocked_by_viewer,
has_blocked_viewer,
is_verified,
is_private,
country_block,
profile_pic_url,
profile_pic_url_hd,
follows {
count
},
followed_by {
count
},
media {
count
}
},
thumbnail_src,
video_views
},
page_info
}
}'
ref: 'tags::show'
do:
- find:
path: media>nodes
do:
- object_new: node
- find:
path: id
do:
- parse
- object_field_set:
object: node
field: id
- find:
path: caption_safe
do:
- parse
- object_field_set:
object: node
field: caption
- find:
path: code
do:
- parse
- variable_prepend:
field: baseurl
joinby: "/"
- object_field_set:
object: node
field: url
- find:
path: is_video
do:
- parse
- object_field_set:
object: node
field: is_video
- find:
path: video_views
do:
- parse
- object_field_set:
object: node
field: vide_views
- find:
path: date
do:
- parse
- normalize:
routine: date_format
args:
format_in: '%s'
format_out: '%Y-%m-%d %H:%M:%S'
- object_field_set:
object: node
field: date
- find:
path: dimensions>width
do:
- parse
- object_field_set:
object: node
field: width
- find:
path: dimensions>height
do:
- parse
- object_field_set:
object: node
field: height
- find:
path: likes>count
do:
- parse
- object_field_set:
object: node
field: likes_count
- find:
path: comments>count
do:
- parse
- object_field_set:
object: node
field: comments_count
- find:
path: comments_disabled
do:
- parse
- object_field_set:
object: node
field: comments_disabled
- find:
path: thumbnail_src
do:
- parse
- object_field_set:
object: node
field: thumbnail
- find:
path: display_src
do:
- parse
- object_field_set:
object: node
field: media
- find:
path: owner>id
do:
- parse
- object_field_set:
object: node
field: owner_id
- find:
path: owner>username
do:
- parse
- object_field_set:
object: node
field: owner_username
- find:
path: owner>full_name
do:
- parse
- object_field_set:
object: node
field: owner_full_name
- find:
path: owner>biography
do:
- parse
- object_field_set:
object: node
field: owner_biography
- find:
path: owner>external_url
do:
- parse
- object_field_set:
object: node
field: owner_external_url
- find:
path: owner>external_url_linkshimmed
do:
- parse
- object_field_set:
object: node
field: owner_external_url_linkshimmed
- find:
path: owner>requested_by_viewer
do:
- parse
- object_field_set:
object: node
field: owner_requested_by_viewer
- find:
path: owner>has_requested_viewer
do:
- parse
- object_field_set:
object: node
field: owner_has_requested_viewer
- find:
path: owner>followed_by_viewer
do:
- parse
- object_field_set:
object: node
field: owner_followed_by_viewer
- find:
path: owner>follows_viewer
do:
- parse
- object_field_set:
object: node
field: owner_follows_viewer
- find:
path: owner>blocked_by_viewer
do:
- parse
- object_field_set:
object: node
field: owner_blocked_by_viewer
- find:
path: owner>has_blocked_viewer
do:
- parse
- object_field_set:
object: node
field: owner_has_blocked_viewer
- find:
path: owner>is_verified
do:
- parse
- object_field_set:
object: node
field: owner_is_verified
- find:
path: owner>is_private
do:
- parse
- object_field_set:
object: node
field: owner_is_private
- find:
path: owner>country_block
do:
- parse
- object_field_set:
object: node
field: owner_country_block
- find:
path: owner>profile_pic_url
do:
- parse
- object_field_set:
object: node
field: owner_profile_pic_url
- find:
path: owner>profile_pic_url_hd
do:
- parse
- object_field_set:
object: node
field: owner_profile_pic_url_hd
- find:
path: owner>follows>count
do:
- parse
- object_field_set:
object: node
field: owner_follows_count
- find:
path: owner>followed_by
do:
- parse
- object_field_set:
object: node
field: owner_followed_by_count
- find:
path: owner>media>count
do:
- parse
- object_field_set:
object: node
field: owner_media_count
- find:
path: likes>nodes
do:
- object_new: likes
- find:
path: user>id
do:
- parse
- object_field_set:
object: likes
field: user_id
- find:
path: user>username
do:
- parse
- object_field_set:
object: likes
field: username
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: likes
field: user_profile_pic
- object_save:
name: likes
to: node
- object_save:
name: nodeInstagram auto-follower. Follows all followers of given user. Requires instagram account. For diggernaut.com service.
Code:
---
config:
agent: Firefox
iterator:
- type: csv
name: user
value: someusername
do:
- walk:
to: https://www.instagram.com/
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- walk:
to:
post: https://www.instagram.com/accounts/login/ajax/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
username: your_instagram_login
password: your_instagram_password
do:
- walk:
to: https://www.instagram.com/<%user%>/
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- find:
path: user>id
do:
- parse
- variable_set: userid
- find:
path: user>followed_by>count
do:
- parse
- variable_set: followed_by
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_user(<%userid%>) {
followed_by.first(<%followed_by%>) {
count,
page_info {
end_cursor,
has_next_page
},
nodes {
id,
is_verified,
followed_by_viewer,
requested_by_viewer,
full_name,
profile_pic_url,
username
}
}
}'
ref: 'relationships::follow_list'
do:
- find:
path: followed_by>nodes
do:
- find:
path: id
do:
- parse
- variable_set: userid
- find:
path: username
do:
- parse
- variable_set: username
- find:
path: requested_by_viewer
do:
- parse
- variable_set: requested_by_viewer
- find:
path: followed_by_viewer
do:
- parse
- variable_set: followed_by_viewer
- variable_get: followed_by_viewer
- if:
match: false
do:
- variable_get: requested_by_viewer
- if:
match: false
do:
- walk:
to:
post: https://www.instagram.com/web/friendships/<%userid%>/follow/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
t: a
do:
- find:
path: body
do:
- parse
- if:
match: too many requests
do:
- exit
else:
- object_new: user
- variable_get: username
- object_field_set:
object: user
field: username
- find:
path: result
do:
- parse
- object_field_set:
object: user
field: result
- object_save:
name: user
- sleep: 60Script to scrape instagram, grabs all user feed data including all followers and follows (requires instagram account). For diggernaut.com service.
Code:
---
config:
agent: Firefox
iterator:
- type: fieldset
fields:
- user: somusername
itemstoget: 30
mode: simple
do:
- walk:
to: https://www.instagram.com/
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- walk:
to:
post: https://www.instagram.com/accounts/login/ajax/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
username: your_instagram_username
password: your_instagram_password
do:
- walk:
to: https://www.instagram.com/<%user%>/
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- find:
path: entry_data>profilepage
do:
- register_set: https://www.instagram.com/p
- variable_set: baseurl
- object_new: user
- find:
path: user>id
do:
- parse
- object_field_set:
object: user
field: id
- variable_set: userid
- find:
path: user>username
do:
- parse
- object_field_set:
object: user
field: username
- find:
path: user>full_name
do:
- parse
- object_field_set:
object: user
field: full_name
- find:
path: user>biography
do:
- parse
- object_field_set:
object: user
field: biography
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: user
field: profile_pic_url
- find:
path: user>profile_pic_url_hd
do:
- parse
- object_field_set:
object: user
field: profile_pic_url_hd
- find:
path: user>external_url
do:
- parse
- object_field_set:
object: user
field: external_url
- find:
path: user>external_url_linkshimmed
do:
- parse
- object_field_set:
object: user
field: external_url_linkshimmed
- find:
path: user>country_block
do:
- parse
- object_field_set:
object: user
field: country_block
- find:
path: user>follows>count
do:
- parse
- object_field_set:
object: user
field: follows
- variable_set: follows
- find:
path: user>followed_by>count
do:
- parse
- object_field_set:
object: user
field: followed_by
- variable_set: followed_by
- find:
path: user>media>page_info>start_cursor
do:
- parse
- variable_set: cursor
- argument_get: itemstoget
- if:
match: all
do:
- find:
path: user>media>count
do:
- parse
- variable_set: items_get
else:
- variable_set: items_get
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_user(<%userid%>) {
followed_by.first(<%followed_by%>) {
count,
page_info {
end_cursor,
has_next_page
},
nodes {
id,
is_verified,
followed_by_viewer,
requested_by_viewer,
full_name,
profile_pic_url,
username
}
}
}'
ref: 'relationships::follow_list'
do:
- find:
path: followed_by>nodes
do:
- object_new: followers
- find:
path: id
do:
- parse
- object_field_set:
object: followers
field: id
- find:
path: username
do:
- parse
- object_field_set:
object: followers
field: username
- find:
path: full_name
do:
- parse
- object_field_set:
object: followers
field: full_name
- find:
path: profile_pic_url
do:
- parse
- object_field_set:
object: followers
field: profile_pic_url
- find:
path: is_verified
do:
- parse
- object_field_set:
object: followers
field: is_verified
- find:
path: followed_by_viewer
do:
- parse
- object_field_set:
object: followers
field: followed_by_viewer
- find:
path: requested_by_viewer
do:
- parse
- object_field_set:
object: followers
field: requested_by_viewer
- object_save:
name: followers
to: user
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_user(<%userid%>) {
follows.first(<%follows%>) {
count,
page_info {
end_cursor,
has_next_page
},
nodes {
id,
is_verified,
followed_by_viewer,
requested_by_viewer,
full_name,
profile_pic_url,
username
}
}
}'
ref: 'relationships::follow_list'
do:
- find:
path: follows>nodes
do:
- object_new: following
- find:
path: id
do:
- parse
- object_field_set:
object: following
field: id
- find:
path: username
do:
- parse
- object_field_set:
object: following
field: username
- find:
path: full_name
do:
- parse
- object_field_set:
object: following
field: full_name
- find:
path: profile_pic_url
do:
- parse
- object_field_set:
object: following
field: profile_pic_url
- find:
path: is_verified
do:
- parse
- object_field_set:
object: following
field: is_verified
- find:
path: followed_by_viewer
do:
- parse
- object_field_set:
object: following
field: followed_by_viewer
- find:
path: requested_by_viewer
do:
- parse
- object_field_set:
object: following
field: requested_by_viewer
- object_save:
name: following
to: user
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_user(<%userid%>) { media.after(<%cursor%>, <%items_get%>) {
count,
nodes {
caption,
code,
comments {
count
},
comments_disabled,
date,
dimensions {
height,
width
},
display_src,
id,
is_video,
likes {
count
},
owner {
id
},
thumbnail_src,
video_views
},
page_info
}
}'
ref: 'users::show'
do:
- find:
path: media>count
do:
- parse
- object_field_set:
object: user
field: media_count
- find:
path: media>nodes
do:
- object_new: nodes
- find:
path: id
do:
- parse
- object_field_set:
object: nodes
field: id
- find:
path: is_video
do:
- parse
- object_field_set:
object: nodes
field: is_video
- find:
path: video_views
do:
- parse
- object_field_set:
object: nodes
field: vide_views
- find:
path: date
do:
- parse
- normalize:
routine: date_format
args:
format_in: '%s'
format_out: '%Y-%m-%d %H:%M:%S'
- object_field_set:
object: nodes
field: date
- find:
path: dimensions>width
do:
- parse
- object_field_set:
object: nodes
field: width
- find:
path: dimensions>height
do:
- parse
- object_field_set:
object: nodes
field: height
- find:
path: likes>count
do:
- parse
- object_field_set:
object: nodes
field: likes_count
- find:
path: comments>count
do:
- parse
- object_field_set:
object: nodes
field: comments_count
- find:
path: comments_disabled
do:
- parse
- object_field_set:
object: nodes
field: comments_disabled
- find:
path: caption_safe
do:
- parse
- object_field_set:
object: nodes
field: caption
- find:
path: thumbnail_src
do:
- parse
- object_field_set:
object: nodes
field: thumbnail
- find:
path: display_src
do:
- parse
- object_field_set:
object: nodes
field: media
- find:
path: code
do:
- parse
- variable_prepend:
field: baseurl
joinby: "/"
- object_field_set:
object: nodes
field: url
- variable_set: node_url
- argument_get: mode
- if:
match: extended
do:
- variable_get: node_url
- walk:
to: value
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: entry_data>postpage>media>comments>nodes
do:
- object_new: comments
- find:
path: '>id'
do:
- parse
- object_field_set:
object: comments
field: id
- find:
path: user>id
do:
- parse
- object_field_set:
object: comments
field: user_id
- find:
path: user>username
do:
- parse
- object_field_set:
object: comments
field: username
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: comments
field: user_profile_pic
- find:
path: text
do:
- parse
- object_field_set:
object: comments
field: text
- find:
path: created_at
do:
- parse:
filter: (\d+)\.\d+
- normalize:
routine: date_format
args:
format_in: '%s'
format_out: '%Y-%m-%d %H:%M:%S'
- object_field_set:
object: comments
field: date
- object_save:
name: comments
to: nodes
- find:
path: entry_data>postpage>media>likes>nodes
do:
- object_new: likes
- find:
path: user>id
do:
- parse
- object_field_set:
object: likes
field: user_id
- find:
path: user>username
do:
- parse
- object_field_set:
object: likes
field: username
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: likes
field: user_profile_pic
- object_save:
name: likes
to: nodes
- sleep: 3
- object_save:
name: nodes
to: user
- object_save:
name: user
[/B]Script for instagram scrape, can be used to get public information from user feed (no login info required). For diggernaut.com service
Code:
---
config:
agent: Firefox
iterator:
- type: fieldset
fields:
- user: somusername
itemstoget: 30
mode: simple
do:
- walk:
to: https://www.instagram.com/<%user%>/
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: config>csrf_token
do:
- parse
- variable_set: token
- find:
path: entry_data>profilepage
do:
- register_set: https://www.instagram.com/p
- variable_set: baseurl
- object_new: user
- find:
path: user>id
do:
- parse
- object_field_set:
object: user
field: id
- variable_set: userid
- find:
path: user>username
do:
- parse
- object_field_set:
object: user
field: username
- find:
path: user>full_name
do:
- parse
- object_field_set:
object: user
field: full_name
- find:
path: user>biography
do:
- parse
- object_field_set:
object: user
field: biography
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: user
field: profile_pic_url
- find:
path: user>profile_pic_url_hd
do:
- parse
- object_field_set:
object: user
field: profile_pic_url_hd
- find:
path: user>external_url
do:
- parse
- object_field_set:
object: user
field: external_url
- find:
path: user>external_url_linkshimmed
do:
- parse
- object_field_set:
object: user
field: external_url_linkshimmed
- find:
path: user>country_block
do:
- parse
- object_field_set:
object: user
field: country_block
- find:
path: user>follows>count
do:
- parse
- object_field_set:
object: user
field: follows
- find:
path: user>followed_by>count
do:
- parse
- object_field_set:
object: user
field: followed_by
- find:
path: user>media>page_info>start_cursor
do:
- parse
- variable_set: cursor
- argument_get: itemstoget
- if:
match: all
do:
- find:
path: user>media>count
do:
- parse
- variable_set: items_get
else:
- variable_set: items_get
- walk:
to:
post: https://www.instagram.com/query/
headers:
x-csrftoken: <%token%>
x-instagram-ajax: 1
x-requested-with: XMLHttpRequest
data:
q: 'ig_user(<%userid%>) { media.after(<%cursor%>, <%items_get%>) {
count,
nodes {
caption,
code,
comments {
count
},
comments_disabled,
date,
dimensions {
height,
width
},
display_src,
id,
is_video,
likes {
count
},
owner {
id
},
thumbnail_src,
video_views
},
page_info
}
}'
ref: 'users::show'
do:
- find:
path: media>count
do:
- parse
- object_field_set:
object: user
field: media_count
- find:
path: media>nodes
do:
- object_new: nodes
- find:
path: id
do:
- parse
- object_field_set:
object: nodes
field: id
- find:
path: is_video
do:
- parse
- object_field_set:
object: nodes
field: is_video
- find:
path: video_views
do:
- parse
- object_field_set:
object: nodes
field: vide_views
- find:
path: date
do:
- parse
- normalize:
routine: date_format
args:
format_in: '%s'
format_out: '%Y-%m-%d %H:%M:%S'
- object_field_set:
object: nodes
field: date
- find:
path: dimensions>width
do:
- parse
- object_field_set:
object: nodes
field: width
- find:
path: dimensions>height
do:
- parse
- object_field_set:
object: nodes
field: height
- find:
path: likes>count
do:
- parse
- object_field_set:
object: nodes
field: likes_count
- find:
path: comments>count
do:
- parse
- object_field_set:
object: nodes
field: comments_count
- find:
path: comments_disabled
do:
- parse
- object_field_set:
object: nodes
field: comments_disabled
- find:
path: caption_safe
do:
- parse
- object_field_set:
object: nodes
field: caption
- find:
path: thumbnail_src
do:
- parse
- object_field_set:
object: nodes
field: thumbnail
- find:
path: display_src
do:
- parse
- object_field_set:
object: nodes
field: media
- find:
path: code
do:
- parse
- variable_prepend:
field: baseurl
joinby: "/"
- object_field_set:
object: nodes
field: url
- variable_set: node_url
- argument_get: mode
- if:
match: extended
do:
- variable_get: node_url
- walk:
to: value
do:
- find:
path: body
do:
- parse:
filter: window\._sharedData\s+\=\s+([^;]+);
- normalize:
routine: json2xml
- to_block
- find:
path: entry_data>postpage>media>comments>nodes
do:
- object_new: comments
- find:
path: '>id'
do:
- parse
- object_field_set:
object: comments
field: id
- find:
path: user>id
do:
- parse
- object_field_set:
object: comments
field: user_id
- find:
path: user>username
do:
- parse
- object_field_set:
object: comments
field: username
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: comments
field: user_profile_pic
- find:
path: text
do:
- parse
- object_field_set:
object: comments
field: text
- find:
path: created_at
do:
- parse:
filter: (\d+)\.\d+
- normalize:
routine: date_format
args:
format_in: '%s'
format_out: '%Y-%m-%d %H:%M:%S'
- object_field_set:
object: comments
field: date
- object_save:
name: comments
to: nodes
- find:
path: entry_data>postpage>media>likes>nodes
do:
- object_new: likes
- find:
path: user>id
do:
- parse
- object_field_set:
object: likes
field: user_id
- find:
path: user>username
do:
- parse
- object_field_set:
object: likes
field: username
- find:
path: user>profile_pic_url
do:
- parse
- object_field_set:
object: likes
field: user_profile_pic
- object_save:
name: likes
to: nodes
- object_save:
name: nodes
to: user
- object_save:
name: user
[/B]