diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2022-04-04 17:32:53 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2022-04-04 17:32:53 -0700 |
| commit | c69a8dadb0426fec10fe38474c2f37ceaebdf316 (patch) | |
| tree | d76899b3b059b82afc06bccbed867555c8c49574 | |
| parent | e2a98a0d47f307e59e2b50f0a3945a2a4f9caaea (diff) | |
| download | sandcrawler-c69a8dadb0426fec10fe38474c2f37ceaebdf316.tar.gz sandcrawler-c69a8dadb0426fec10fe38474c2f37ceaebdf316.zip | |
ingest: drive.google.com ingest support
| -rw-r--r-- | python/sandcrawler/html.py | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 50183be..6e5d2d6 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -343,6 +343,14 @@ def extract_fulltext_url(html_url: str, html_body: bytes) -> Dict[str, str]: url = html_url + "pdf" return dict(pdf_url=url, technique="jmir-url") + # Google Drive + # this is assuming it is a PDF + if "drive.google.com/file/d/" in html_url and "/view" in html_url: + gdrive_id = html_url.split('/')[5] + if len(gdrive_id) > 10: + # https://drive.google.com/uc?export=download&id=15DnbNMZTbRHHqKj8nFaikGSd1-OyoJ24 + return dict(pdf_url=f"https://drive.google.com/uc?export=download&id={gdrive_id}", technique="google-drive") + ### below here we are doing guesses # generic guess: try current URL plus .pdf, if it exists in the HTML body |