通过search_word 在谷歌学术上搜索论文并获取论文标题、bib引用、下载链接以及摘要，目前只搞了论文标题和下载链接

get_paper_title_bib_download_url.py

from genericpath import getctime
from urllib import parse
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from webdriver_manager.utils import download_file

search_word = 'ethereum smart contract'
query = '+'.join(search_word.split(' '))

url = 'https://scholar.google.com/scholar?hl=en&start=%d&q=%s'
driver = webdriver.Chrome(ChromeDriverManager().install())

def get_title(paper_element):
    title = paper_element.find_element_by_class_name('gs_rt')
    return title.text

def get_cite(paper_element):
    pass

def get_download_url(paper_element):
    try:
        download_url = paper_element.find_element_by_class_name('gs_or_ggsm')
    except Exception as e:
        return 'no_download_url'
    download_url = download_url.find_element_by_tag_name('a')
    if '[PDF]' in download_url.text:
        return download_url.get_attribute('href')
    return 'no_pdf_download_url'

def get_abstract(paper_element):
    pass

def get_info(start):
    driver.get(url % (start, query))
    papers = driver.find_elements_by_xpath("//div[@class='gs_r gs_or gs_scl']")
    for paper in papers:
        title, cite, download_url = get_title(paper), get_cite(paper), get_download_url(paper)
        with open('papers.txt', 'a', encoding='utf-8') as a:
            a.write('%s#%s\n' % (title, download_url))

for i in range(1, 100):
    print('[INFO] ===========================', i)
    get_info(i * 10)

# driver.close()