From 1ca59d0ee105db368f338c5d0f8cb24396e05398 Mon Sep 17 00:00:00 2001
From: Alfian Ali Murtadlo <115053112+AlfianAliM@users.noreply.github.com>
Date: Wed, 2 Oct 2024 08:25:46 +0700
Subject: [PATCH 1/2] Update crawl_google_scholar_citation.py

---
 .../crawl_google_scholar_citation.py          | 25 +++++++++++++++----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/web_programming/crawl_google_scholar_citation.py b/web_programming/crawl_google_scholar_citation.py
index 5f2ccad5f..fee483686 100644
--- a/web_programming/crawl_google_scholar_citation.py
+++ b/web_programming/crawl_google_scholar_citation.py
@@ -6,20 +6,33 @@ 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.
+    Returns the citation number for a publication based on its title, journal, volume, 
+    pages, and year of publication.
+    
+    Parameters:
+    - base_url: The base URL for making requests to Google Scholar.
+    - params: A dictionary containing the publication information.
+    
+    Returns:
+    - A string containing the number of citations.
     """
+    # Send a GET request to the URL with the specified parameters
     soup = BeautifulSoup(
         requests.get(base_url, params=params, timeout=10).content, "html.parser"
     )
+    
+    # Find the div element with class 'gs_ri' that contains citation information
     div = soup.find("div", attrs={"class": "gs_ri"})
+    
+    # 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")
-    return anchors[2].get_text()
-
+    
+    return anchors[2].get_text()  # Return the text from the third link
 
 if __name__ == "__main__":
+    # Define parameters for the publication whose citation is to be searched
     params = {
         "title": (
             "Precisely geometry controlled microsupercapacitors for ultrahigh areal "
@@ -29,6 +42,8 @@ if __name__ == "__main__":
         "volume": 30,
         "pages": "3979-3990",
         "year": 2018,
-        "hl": "en",
+        "hl": "en",  # Language to be used (English)
     }
+    
+    # Call the get_citation function with the specified URL and parameters
     print(get_citation("https://scholar.google.com/scholar_lookup", params=params))

From 355ae4c6c37dde4dc343d50b99fb1ff2cca505d1 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 2 Oct 2024 01:27:58 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 web_programming/crawl_google_scholar_citation.py | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/web_programming/crawl_google_scholar_citation.py b/web_programming/crawl_google_scholar_citation.py
index fee483686..12072d0dd 100644
--- a/web_programming/crawl_google_scholar_citation.py
+++ b/web_programming/crawl_google_scholar_citation.py
@@ -6,15 +6,16 @@ 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:
     """
-    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.
-    
+
     Parameters:
     - base_url: The base URL for making requests to Google Scholar.
     - params: A dictionary containing the publication information.
-    
+
     Returns:
     - A string containing the number of citations.
     """
@@ -22,15 +23,16 @@ def get_citation(base_url: str, params: dict) -> str:
     soup = BeautifulSoup(
         requests.get(base_url, params=params, timeout=10).content, "html.parser"
     )
-    
+
     # Find the div element with class 'gs_ri' that contains citation information
     div = soup.find("div", attrs={"class": "gs_ri"})
-    
+
     # 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")
-    
+
     return anchors[2].get_text()  # Return the text from the third link
 
+
 if __name__ == "__main__":
     # Define parameters for the publication whose citation is to be searched
     params = {
@@ -44,6 +46,6 @@ if __name__ == "__main__":
         "year": 2018,
         "hl": "en",  # Language to be used (English)
     }
-    
+
     # Call the get_citation function with the specified URL and parameters
     print(get_citation("https://scholar.google.com/scholar_lookup", params=params))