Last active
June 19, 2021 08:53
-
-
Save avandeursen/4bc4afd320a3934e5b9aba48bf9b57f7 to your computer and use it in GitHub Desktop.
Turn a publication list in an Elsevier Pure web page into a list of bibtex entries with urls back to Pure.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import requests | |
from bs4 import BeautifulSoup | |
# Set to the PURE page you'd like to get the bibtex entries from. Here's mine: | |
pure = "https://pure.tudelft.nl/portal/en/persons/a-van-deursen(949eb2cc-4db0-4f33-bd56-13425fa5c24a)/publications.html?page=0" | |
class BibTexEntry: | |
def __init__(self, entry): | |
self.entry = entry | |
def withField(self, field): | |
start = self.entry.rstrip("}") | |
self.entry = start + " " + field + ",\n}" | |
return self | |
def withURL(self, url): | |
return self.withField("url = \"" + url + "\"") | |
def withGroup(self, group): | |
return self.withField("group = \"" + group + "\"") | |
def withCode(self): | |
return self.withField("code = {I-ISS-07}") | |
def inProceedings(self): | |
self.entry = self.entry.replace('@inbook{', '@inproceedings{') | |
return self | |
def process(self, url): | |
return ( | |
self | |
.withURL(url) | |
.withGroup("SE") | |
.withCode() | |
.inProceedings() | |
.entry | |
) | |
def soupPage(url): | |
response = requests.get(url) | |
soup = BeautifulSoup(response.content, "html.parser") | |
return soup | |
def titleLinks(researchOutput) : | |
anchors = researchOutput.select("div.rendering_researchoutput h2.title a.link") | |
links = list(map(lambda a: a['href'], anchors)) | |
return links | |
def exportPage(titleLink) : | |
export = titleLink.replace('.html', '/export.html') | |
return soupPage(export) | |
def bibtex(page) : | |
bibdiv = page.select("div.rendering_bibtex") | |
return bibdiv[0].text | |
def getBibs(paperListURL) : | |
links = titleLinks(soupPage(paperListURL)) | |
for paperURL in links : | |
bib = bibtex(exportPage(paperURL)) | |
print(BibTexEntry(bib).process(paperURL)) | |
getBibs(pure) | |
# Copyright 2017 Arie van Deursen | |
# Licensed under the Apache License, Version 2.0 (the "License"); | |
# you may not use this file except in compliance with the License. | |
# You may obtain a copy of the License at | |
# http://www.apache.org/licenses/LICENSE-2.0 | |
# Unless required by applicable law or agreed to in writing, software | |
# distributed under the License is distributed on an "AS IS" BASIS, | |
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
# See the License for the specific language governing permissions and | |
# limitations under the License. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, Great work! this is exactly what I was looking for. Would you how would I run this code on a WordPress site?