mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-02-06 17:40:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2024-10-02 01:27:58 +00:00
parent 1ca59d0ee1
commit 355ae4c6c3
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
web_programming/crawl_google_scholar_citation.py
View File

@ -6,15 +6,16 @@ using title and year of publication, and volume and pages of journal.
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
def get_citation(base_url: str, params: dict) -> str: def get_citation(base_url: str, params: dict) -> str:
""" """
Returns the citation number for a publication based on its title, journal, volume, Returns the citation number for a publication based on its title, journal, volume,
pages, and year of publication. pages, and year of publication.
Parameters: Parameters:
- base_url: The base URL for making requests to Google Scholar. - base_url: The base URL for making requests to Google Scholar.
- params: A dictionary containing the publication information. - params: A dictionary containing the publication information.
Returns: Returns:
- A string containing the number of citations. - A string containing the number of citations.
""" """
@ -22,15 +23,16 @@ def get_citation(base_url: str, params: dict) -> str:
soup = BeautifulSoup( soup = BeautifulSoup(
requests.get(base_url, params=params, timeout=10).content, "html.parser" requests.get(base_url, params=params, timeout=10).content, "html.parser"
) )
# Find the div element with class 'gs_ri' that contains citation information # Find the div element with class 'gs_ri' that contains citation information
div = soup.find("div", attrs={"class": "gs_ri"}) div = soup.find("div", attrs={"class": "gs_ri"})
# Find all links in the div and retrieve the third link (the citation count) # Find all links in the div and retrieve the third link (the citation count)
anchors = div.find("div", attrs={"class": "gs_fl"}).find_all("a") anchors = div.find("div", attrs={"class": "gs_fl"}).find_all("a")
return anchors[2].get_text() # Return the text from the third link return anchors[2].get_text() # Return the text from the third link
if __name__ == "__main__": if __name__ == "__main__":
# Define parameters for the publication whose citation is to be searched # Define parameters for the publication whose citation is to be searched
params = { params = {
@ -44,6 +46,6 @@ if __name__ == "__main__":
"year": 2018, "year": 2018,
"hl": "en", # Language to be used (English) "hl": "en", # Language to be used (English)
} }
# Call the get_citation function with the specified URL and parameters # Call the get_citation function with the specified URL and parameters
print(get_citation("https://scholar.google.com/scholar_lookup", params=params)) print(get_citation("https://scholar.google.com/scholar_lookup", params=params))