github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[instagram] extract '__additionalDataLoaded' (#391)

Browse Source 
The '_sharedData' of Post pages is missing its 'graphql' part for
logged in users. This data is now included in the parameters of a
function call to '__additionalDataLoaded(...)'

And, of course, video extraction with youtube-dl broke because of
this change as well.
This commit is contained in:
Mike Fährmann
2019-10-29 16:00:31 +01:00
parent 5af291ba5c
commit 5fa6ff04dd
1 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
gallery_dl/extractor/instagram.py
View File

@@ -101,8 +101,16 @@ class InstagramExtractor(Extractor):
def _extract_shared_data(self, url): def _extract_shared_data(self, url):
page = self.request(url).text page = self.request(url).text
data = text.extract(page, 'window._sharedData = ', ';</script>')[0] shared_data, pos = text.extract(
return json.loads(data) page, 'window._sharedData =', ';</script>')
additional_data, pos = text.extract(
page, 'window.__additionalDataLoaded(', ');</script>', pos)
data = json.loads(shared_data)
if additional_data:
next(iter(data['entry_data'].values()))[0] = \
json.loads(additional_data.partition(',')[2])
return data
def _extract_postpage(self, url): def _extract_postpage(self, url):
shared_data = self._extract_shared_data(url) shared_data = self._extract_shared_data(url)