谷歌学术得到论文被引用信息

目的：利用谷歌学术，得到一篇论文中所有被引用文献信息

from time import sleep
from urllib import parse

from selenium import webdriver


class GetBibs():
    def __init__(self, gg_search_url) -> None:
        self.gg_search_url = gg_search_url
        # 启用带插件的浏览器
        option = webdriver.ChromeOptions()
        option.add_argument("--user-data-dir=" + option_path)
        self.browser = webdriver.Chrome(options=option)  # 打开chrome浏览器

    # 进入被引用文献链接
    def get_title_to_google_scholar(self, paper_title):
        strto_pn = parse.quote(paper_title)
        url = self.gg_search_url + strto_pn
        self.browser.get(url)
        # 等待词条加载,得到数据
        for i in range(100):
            try:
                element = self.browser.find_element_by_css_selector("[class='gs_r gs_or gs_scl']")
                element = element.find_element_by_css_selector("[class='gs_fl']")
                links = element.find_elements_by_xpath("a")
                print(links[2].get_attribute('href'))
                element = links[2]
                element.click()

                break
            except:
                sleep(0.1)
        self.get_data_from_google_scholar()

    def get_data_from_google_scholar(self):
        old_url = self.browser.current_url
        for page_count in range(0, 10):
            print(self.browser.current_url)
            print(self.browser.title)
            url_head = old_url.split('scholar?')[0]
            url_tail = old_url.split('scholar?')[1]
            url = url_head + 'scholar?start=' + str(10 * page_count) + '&' + url_tail
            self.browser.get(url)
            print(self.browser.current_url)
            print(self.browser.title)
            # 等待词条加载,得到数据
            for i in range(100):
                try:
                    elements = self.browser.find_elements_by_css_selector("[class='gs_r gs_or gs_scl']")
                    for element in elements:
                        content = element.find_element_by_css_selector("[class='gs_rt']").text
                        print('标题：', content)

                        content = element.find_element_by_css_selector("[class='gs_a']").text
                        temp_content = content.split(' - ')[-2]
                        article = temp_content.split(', ')[0]
                        print('期刊：', article)

                        year = temp_content.split(', ')[1]
                        print('年月：', year)

                        temp_content = element.find_element_by_css_selector("[class='gs_fl']").text
                        cited = temp_content.split(' ')[0].split('：')[-1]
                        print('被引用：', cited)
                        print("\n")
                    break
                except:
                    sleep(0.1)
            sleep(10)


option_path = r"C:/Users/Administrator/AppData/Local/Google/Chrome/User Data - 副本/"  # 使浏览器能用你自定义的设置，否则Selenium创建的浏览器对象是默认设置，一些插件就不能用了
gg_search_url = r'https://scholar.google.com/scholar?hl=zh-CN&as_sdt=0%2C5&inst=1597255436240989024&q='  # 在执行代码之前，先打开搜索页面，把类似的网址复制到这里，等号=后面就是一会儿要搜索的内容
get_bibs = GetBibs(gg_search_url)
# %% **********************以上定义爬虫对象，以下开始爬取*******************************
paper_titles = {  # 要爬取的论文，key用于标记，value是论文题目。下面是一些样例
    "DMCNN": 'Deep Multi-Scale Convolutional Neural Network for Dynamic Scene Deblurring',
}

for k in paper_titles.keys():
    get_bibs.get_title_to_google_scholar(paper_titles[k])

结果

参考代码：

使用Selenium从IEEE与谷歌学术批量爬取BibTex文献引用_https://www.cnblogs.com/qizhou/-CSDN博客
https://github.com/Dao-zhi/GoogleScholarGUI
错误解决方法 ：
selenium之加载chrome配置 - 越来越努力 - 博客园