66 lines
2.1 KiB
Plaintext
66 lines
2.1 KiB
Plaintext
|
#!/usr/bin/env python3
|
||
|
|
"""Qutebrowser userscript scraping the current web page for DOIs and downloading
|
||
|
|
corresponding bibtex information.
|
||
|
|
Set the environment variable 'QUTE_BIB_FILEPATH' to indicate the path to
|
||
|
|
download to. Otherwise, bibtex information is downloaded to '/tmp' and hence
|
||
|
|
deleted at reboot.
|
||
|
|
Installation: see qute://help/userscripts.html
|
||
|
|
Inspired by
|
||
|
|
https://ocefpaf.github.io/python4oceanographers/blog/2014/05/19/doi2bibtex/
|
||
|
|
"""
|
||
|
|
|
||
|
|
import os
|
||
|
|
import sys
|
||
|
|
import re
|
||
|
|
from collections import Counter
|
||
|
|
from urllib import parse as url_parse
|
||
|
|
from urllib import request as url_request
|
||
|
|
|
||
|
|
|
||
|
|
FIFO_PATH = os.getenv("QUTE_FIFO")
|
||
|
|
|
||
|
|
def message_fifo(message, level="warning"):
|
||
|
|
"""Send message to qutebrowser FIFO. The level must be one of 'info',
|
||
|
|
'warning' (default) or 'error'."""
|
||
|
|
with open(FIFO_PATH, "w") as fifo:
|
||
|
|
fifo.write("message-{} '{}'".format(level, message))
|
||
|
|
|
||
|
|
|
||
|
|
source = os.getenv("QUTE_TEXT")
|
||
|
|
with open(source) as f:
|
||
|
|
text = f.read()
|
||
|
|
|
||
|
|
# find DOIs on page using regex
|
||
|
|
dval = re.compile(r'(10\.(\d)+/([^(\s\>\"\<)])+)')
|
||
|
|
# https://stackoverflow.com/a/10324802/3865876, too strict
|
||
|
|
# dval = re.compile(r'\b(10[.][0-9]{4,}(?:[.][0-9]+)*/(?:(?!["&\'<>])\S)+)\b')
|
||
|
|
dois = dval.findall(text)
|
||
|
|
dois = Counter(e[0] for e in dois)
|
||
|
|
try:
|
||
|
|
doi = dois.most_common(1)[0][0]
|
||
|
|
except IndexError:
|
||
|
|
message_fifo("No DOIs found on page")
|
||
|
|
sys.exit()
|
||
|
|
message_fifo("Found {} DOIs on page, selecting {}".format(len(dois), doi),
|
||
|
|
level="info")
|
||
|
|
|
||
|
|
# get bibtex data corresponding to DOI
|
||
|
|
url = "https://dx.doi.org/" + url_parse.quote(doi)
|
||
|
|
headers = dict(Accept='text/bibliography; style=bibtex')
|
||
|
|
request = url_request.Request(url, headers=headers)
|
||
|
|
response = url_request.urlopen(request)
|
||
|
|
status_code = response.getcode()
|
||
|
|
if status_code >= 400:
|
||
|
|
message_fifo("Request returned {}".format(status_code))
|
||
|
|
sys.exit()
|
||
|
|
|
||
|
|
# obtain content and format it
|
||
|
|
bibtex = response.read().decode("utf-8").strip()
|
||
|
|
bibtex = bibtex.replace(" ", "\n ", 1).\
|
||
|
|
replace("}, ", "},\n ").replace("}}", "}\n}")
|
||
|
|
|
||
|
|
# append to file
|
||
|
|
bib_filepath = os.getenv("QUTE_BIB_FILEPATH", "/tmp/qute.bib")
|
||
|
|
with open(bib_filepath, "a") as f:
|
||
|
|
f.write(bibtex + "\n\n")
|