Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add PLAYA-PDF and update release dates #17

Open
wants to merge 17 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 37 additions & 33 deletions README.md

Large diffs are not rendered by default.

23 changes: 17 additions & 6 deletions benchmark.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
import pdfminer
import pdfplumber
import pdfrw
import playa
import pypdf
import pypdfium2
import tika
Expand All @@ -30,6 +31,7 @@
pdfplubmer_get_text,
pdfrw_watermarking,
pdftotext_get_text,
playa_get_text,
pymupdf_get_text,
pymupdf_image_extraction,
pymupdf_watermarking,
Expand Down Expand Up @@ -172,7 +174,7 @@ def write_single_result(
version=pypdf.__version__,
watermarking_function=pypdf_watermarking,
license="BSD 3-Clause",
last_release_date="2023-08-26",
last_release_date="2025-02-09",
image_extraction_function=pypdf_image_extraction,
),
"pdfminer": Library(
Expand All @@ -182,7 +184,7 @@ def write_single_result(
text_extraction_function=lambda n: pdfminder_extract_text(BytesIO(n)),
version=pdfminer.__version__,
license="MIT/X",
last_release_date="2022-11-05",
last_release_date="2024-07-06",
image_extraction_function=pdfminer_image_extraction,
),
"pdfplumber": Library(
Expand All @@ -192,7 +194,7 @@ def write_single_result(
text_extraction_function=pdfplubmer_get_text,
version=pdfplumber.__version__,
license="MIT",
last_release_date="2023-07-29",
last_release_date="2025-01-01",
dependencies="pdfminer.six",
),
"pymupdf": Library(
Expand All @@ -205,7 +207,7 @@ def write_single_result(
image_extraction_function=pymupdf_image_extraction,
dependencies="MuPDF",
license="GNU AFFERO GPL 3.0 / Commerical",
last_release_date="2023-08-24",
last_release_date="2025-02-06",
),
"pdftotext": Library(
"pdftotext",
Expand All @@ -226,7 +228,7 @@ def write_single_result(
version="2.1.16",
watermarking_function=None,
license="AGPL/Commercial",
last_release_date="2023-06-23",
last_release_date="2024-08-03",
),
"pdfium": Library(
"pypdfium2",
Expand All @@ -237,7 +239,7 @@ def write_single_result(
watermarking_function=None,
image_extraction_function=pdfium_image_extraction,
license="Apache-2.0 or BSD-3-Clause",
last_release_date="2023-07-04",
last_release_date="2024-12-19",
dependencies="PDFium (Foxit/Google)",
),
"pdfrw": Library(
Expand All @@ -251,5 +253,14 @@ def write_single_result(
last_release_date="2017-09-18",
dependencies="",
),
"playa": Library(
"playa",
"playa",
"https://pypi.org/project/playa-pdf/",
text_extraction_function=playa_get_text,
version=playa.__version__,
license="MIT",
last_release_date="2025-02-20",
),
}
main(docs, libraries)
Loading