Python/web_programming/crawl_google_scholar_citation.py
Maxim Smolskiy 2702bf9400
Enable ruff S113 rule (#11375)
* Enable ruff S113 rule

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-04-21 19:34:18 +02:00

35 lines
984 B
Python

"""
Get the citation from google scholar
using title and year of publication, and volume and pages of journal.
"""
import requests
from bs4 import BeautifulSoup
def get_citation(base_url: str, params: dict) -> str:
"""
Return the citation number.
"""
soup = BeautifulSoup(
requests.get(base_url, params=params, timeout=10).content, "html.parser"
)
div = soup.find("div", attrs={"class": "gs_ri"})
anchors = div.find("div", attrs={"class": "gs_fl"}).find_all("a")
return anchors[2].get_text()
if __name__ == "__main__":
params = {
"title": (
"Precisely geometry controlled microsupercapacitors for ultrahigh areal "
"capacitance, volumetric capacitance, and energy density"
),
"journal": "Chem. Mater.",
"volume": 30,
"pages": "3979-3990",
"year": 2018,
"hl": "en",
}
print(get_citation("https://scholar.google.com/scholar_lookup", params=params))