diff options
| author | Gertjan van den Burg <gertjanvandenburg@gmail.com> | 2019-08-19 18:28:34 +0100 |
|---|---|---|
| committer | Gertjan van den Burg <gertjanvandenburg@gmail.com> | 2019-08-19 18:28:45 +0100 |
| commit | b98d95d1b038fdf4d21b84ab66eaec6d122569f6 (patch) | |
| tree | ce5e3c706554376b3924ff51fff5c8d42e763476 | |
| parent | Unify ``get_paper_info`` (diff) | |
| download | paper2remarkable-b98d95d1b038fdf4d21b84ab66eaec6d122569f6.tar.gz paper2remarkable-b98d95d1b038fdf4d21b84ab66eaec6d122569f6.zip | |
Ensure filename is ascii using unidecode
| -rwxr-xr-x | arxiv2remarkable.py | 2 | ||||
| -rw-r--r-- | poetry.lock | 11 | ||||
| -rw-r--r-- | pyproject.toml | 1 |
3 files changed, 13 insertions, 1 deletions
diff --git a/arxiv2remarkable.py b/arxiv2remarkable.py index 01ab273..83a89bb 100755 --- a/arxiv2remarkable.py +++ b/arxiv2remarkable.py @@ -28,6 +28,7 @@ import sys import tempfile import time import titlecase +import unidecode import urllib.parse GITHUB_URL = "https://github.com/GjjvdBurg/arxiv2remarkable" @@ -158,6 +159,7 @@ class Provider(metaclass=abc.ABCMeta): title_part = titlecase.titlecase(title).replace(" ", "_") year_part = info["date"].split("/")[0] name = author_part + "_-_" + title_part + "_" + year_part + ".pdf" + name = unidecode.unidecode(name) self.log("Created filename: %s" % name) return name diff --git a/poetry.lock b/poetry.lock index 322114d..272967c 100644 --- a/poetry.lock +++ b/poetry.lock @@ -137,6 +137,14 @@ version = "0.14.1" [[package]] category = "main" +description = "ASCII transliterations of Unicode text" +name = "unidecode" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*" +version = "1.1.1" + +[[package]] +category = "main" description = "HTTP library with thread-safe connection pooling, file post, and more." name = "urllib3" optional = false @@ -152,7 +160,7 @@ python-versions = "*" version = "0.5.4" [metadata] -content-hash = "21a857f686e73e377feae7bf7c09ed5933d51a3f90ca77315408a3d7fc362c42" +content-hash = "51a0dc0e8f6e6e23395cd5aca6a81e9b3aa121ec86f120f1304f2142eb2b65b0" python-versions = "^3.5" [metadata.hashes] @@ -170,5 +178,6 @@ six = ["3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c", "d16a sortedcontainers = ["974e9a32f56b17c1bac2aebd9dcf197f3eb9cd30553c5852a3187ad162e1a03a", "d9e96492dd51fae31e60837736b38fe42a187b5404c16606ff7ee7cd582d4c60"] soupsieve = ["466910df7561796a60748826781ebe9a888f7a1668a636ae86783f44d10aae73", "87db12ae79194f0ff9808d2b1641c4f031ae39ffa3cab6b907ea7c1e5e5ed445"] unicodecsv = ["018c08037d48649a0412063ff4eda26eaa81eff1546dbffa51fa5293276ff7fc"] +unidecode = ["1d7a042116536098d05d599ef2b8616759f02985c85b4fef50c78a5aaf10822a", "2b6aab710c2a1647e928e36d69c21e76b453cd455f4e2621000e54b2a9b8cce8"] urllib3 = ["61bf29cada3fc2fbefad4fdf059ea4bd1b4a86d2b6d15e1c7c0b582b9752fe39", "de9529817c93f27c8ccbfead6985011db27bd0ddfcdb2d86f3f663385c6a9c22"] wand = ["c52d647a34205f9b3948baae739db461a7379a04818548fe8042b5ce751ea6ea", "e2e08e19a37c61e85eaa307fe319889af46fe4cac6c23e3ae668b96be3e497ff"] diff --git a/pyproject.toml b/pyproject.toml index a211300..7e9c629 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -10,6 +10,7 @@ python = "^3.5" bs4 = "^0.0.1" requests = "^2.21" pdfplumber = "^0.5.12" +unidecode = "^1.1" [tool.poetry.dev-dependencies] |
