diff options
Diffstat (limited to 'scraper/util.py')
| -rw-r--r-- | scraper/util.py | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/scraper/util.py b/scraper/util.py index 1b1a0a9b..bb210012 100644 --- a/scraper/util.py +++ b/scraper/util.py @@ -174,6 +174,10 @@ class RawPaper(object): def __init__(self, paper_id): self.paper_id = paper_id data = read_json(paper_path('raw_papers', paper_id)) + # {'responseType': 'CANONICAL', 'canonicalId': '02ccd5f0eb9a48a6af088197b950fb30a8e3abcc', 'canonicalSlug': 'Scaling-for-Multimodal-3-D-Object-Detection-Stanford'} + if 'responseType' in data and data['responseType'] == 'CANONICAL': + data = read_json(paper_path('raw_papers', data['canonicalId'])) + # print(data) if 'paper' not in data: print(data) @@ -206,6 +210,7 @@ class RawPaper(object): if 'alternatePaperLinks' in self.data: for link in self.data['alternatePaperLinks']: paper_links.append(url_part(link)) + return paper_links def pdf_links(self): return [ link for link in self.paper_links() if 'pdf' in link ] def doi_links(self): |