Python实现搜索Google Scholar论文信息的示例代码

import requests
from bs4 import BeautifulSoup
from tqdm import tqdm
from pybtex.database import BibliographyData, Entry
from pybtex.database.input import bibtex
import pandas as pd
import time
import json
 
import random
 
 
def search_doi(doi):
    '''根据doi查论文详细信息'''
    url = f'https://api.crossref.org/works/{doi}'
    response = requests.get(url)
    result = None
    if response.status_code == 200:
        result = response.json()['message']
    else:
        print('Error occurred')
    return result
 
# doi = 'https://dl.acm.org/doi/abs/10.1145/3394486.3403237'
# result = search_doi(doi)
# print(f"Title: {result['title'][0]}:{result['subtitle'][0]}")
# print(f"Author(s): {', '.join(author['given'] + ' ' + author['family'] for author in result['author'])}")
# print(f"Journal: {result['container-title'][0]}")
# print(f"Publication Date: {result['published-print']['date-parts'][0][0]}")
 
 
def search_cite(atid):
    '''根据atid查cite'''
    url = f'https://scholar.google.com/scholar?q=info:{atid}:scholar.google.com/&output=cite&scirp=8&hl=zh-CN'
    resp = requests.get(url)
    soup = BeautifulSoup(resp.text, 'lxml')
    result = {}
    for item in soup.find_all('tr'):
        cith = item.find('th', class_='gs_cith').getText()
        citr = item.find('div', class_='gs_citr').getText()
        result[cith] = citr
    return result
 
# result = search_cite('_goqYZv1zjMJ')
# print(result)
 
 
 
# 更改节点配置
def change_clash_node(node_name=None):
    # Clash API的URL和密码
    url = 'http://127.0.0.1:15043/proxies/