Checks a latex .bib file for links. If the script finds links, it tries to reach them to see if they are still alive.

check_reference_links.py

# needs     bibtexparser==0.6.2, argparse
"""
    Parses a Bib file and checks if all links are available
"""

# imports
import bibtexparser
import argparse
import re
import requests

# arguments
parser = argparse.ArgumentParser(description='Parses a Bib file and checks if all links are available')
parser.add_argument('-bf', '--bib_file', type=str, default="references.bib", help='The bib file to check')
args = parser.parse_args()


# check url
def verify_url(url, bib_entry_id, key,  value, print_only_error=False):
    r = requests.head(url)
    if print_only_error and r.ok: return r.ok# guard clause
    status = "OK" if r.ok else "ERROR"
    print("\n{} DOI ({})".format(bib_entry_id, status))
    print("\t{}: {}".format(key,value))
    print("\tStatus: (OK={status},Code:{status_code}, is_redirect:{redirect}) ".format(status=r.ok, status_code=r.status_code, redirect=r.is_redirect))

    return r.ok

# walk through bib file and verify links
LINKS_NOT_FOUND = []
with open(args.bib_file) as bibtex_file:
    db = bibtexparser.load(bibtex_file)
    for entry_key, bib_entry in db.entries_dict.items():
        for k,v in bib_entry.items():
            # check all links
            value_is_link =  re.match(r"^http.?://.+?$", v)
            if value_is_link:
                if not verify_url(v,entry_key, k, v): LINKS_NOT_FOUND.append(entry_key)

            # check dois
            value_is_doi = k == "doi"
            if value_is_doi:
                cleaned_doi =  re.sub(r"[\{\}\\]","",v)
                doi_url = "https://doi.org/"+cleaned_doi
                if not verify_url(doi_url,entry_key, k, v): LINKS_NOT_FOUND.append(entry_key)

LINKS_NOT_FOUND=set(sorted(LINKS_NOT_FOUND))
if len(LINKS_NOT_FOUND)==0:
    print("Everything seems to be ok.")
else:
    print("'{}' contain(s) invalid links.".format(",".join(LINKS_NOT_FOUND)))
print("Done. Bye Bye.")