bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-07-03 13:58:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #53 from JackDallas/add-more-insta-fields

Browse Source 
Add more fields to the instagram scraper
This commit is contained in:
JustAnotherArchivist
2020-02-09 23:48:59 +00:00
committed by GitHub
parent 6df351772e 9568028bf9
commit 82a87b7b5a
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
snscrape/modules/instagram.py
View File

@@ -16,6 +16,11 @@ class InstagramPost(typing.NamedTuple, snscrape.base.Item):
content: str content: str
thumbnailUrl: str thumbnailUrl: str
displayUrl: str displayUrl: str
username: str
likes: int
comments: int
commentsDisabled: bool
isVideo: bool
def __str__(self): def __str__(self):
return self.cleanUrl return self.cleanUrl
@@ -57,7 +62,8 @@ class InstagramCommonScraper(snscrape.base.Scraper):
def _response_to_items(self, response): def _response_to_items(self, response):
for node in response[self._responseContainer][self._edgeXToMedia]['edges']: for node in response[self._responseContainer][self._edgeXToMedia]['edges']:
code = node['node']['shortcode'] code = node['node']['shortcode']
usernameQuery = '?taken-by=' + node['node']['owner']['username'] if 'username' in node['node']['owner'] else '' username = node['node']['owner']['username'] if 'username' in node['node']['owner'] else ''
usernameQuery = '?taken-by=' + username
cleanUrl = f'https://www.instagram.com/p/{code}/' cleanUrl = f'https://www.instagram.com/p/{code}/'
yield InstagramPost( yield InstagramPost(
cleanUrl = cleanUrl, cleanUrl = cleanUrl,
@@ -66,6 +72,11 @@ class InstagramCommonScraper(snscrape.base.Scraper):
content = node['node']['edge_media_to_caption']['edges'][0]['node']['text'] if len(node['node']['edge_media_to_caption']['edges']) else None, content = node['node']['edge_media_to_caption']['edges'][0]['node']['text'] if len(node['node']['edge_media_to_caption']['edges']) else None,
thumbnailUrl = node['node']['thumbnail_src'], thumbnailUrl = node['node']['thumbnail_src'],
displayUrl = node['node']['display_url'], displayUrl = node['node']['display_url'],
username = username,
likes = node['node']['edge_media_preview_like']['count'],
comments = node['node']['edge_media_to_comment']['count'],
commentsDisabled = node['node']['comments_disabled'],
isVideo = node['node']['is_video'],
) )
def _check_initial_page_callback(self, r): def _check_initial_page_callback(self, r):