刘耀文

pip install get_bibtex

from apiModels.get_bibtex_from_crossref import GetBibTex
from apiModels.get_bibtex_from_google_scholar import GetBibTexFromGoogleScholar

if __name__ == '__main__':
    google_scholar_api_key = "your_google_scholar_api_key"
    get_bibtex_from_crossref = GetBibTex("[email protected]")
    get_bibtex_from_google_scholar = GetBibTexFromGoogleScholar(google_scholar_api_key, GetBibTexFromGoogleScholar.APA)

    with open("inputfile/Bibliographyraw.txt", "r", encoding='utf-8') as f:
        raws = f.readlines()
    
    # get bibtex from CrossRef and failed search results
    success_bibtexs_crossref, failed_results = get_bibtex_from_crossref.get_bibtexs(raws)
    
    # for each failed search result, get bibtex from Google Scholar
    success_bibtexs_google, failed_results = get_bibtex_from_google_scholar.get_bibtexs(failed_results)

    with open("outputfile/BibliographyCrossRef.txt", "w", encoding='utf-8') as f:
        for bibtex in success_bibtexs_crossref:
            f.write(bibtex)

    with open("outputfile/BibliographyGoogleScholar.txt", "w", encoding='utf-8') as f:
        for index, bibtex in enumerate(success_bibtexs_google):
            f.write("[]".format(index) + " " + bibtex + "\n")

    with open("outputfile/not_find.txt", "w", encoding='utf-8') as f:
        for result in failed_results:
            f.write(result+"\n")

    print("find bibtex from CrossRef: ", len(success_bibtexs_crossref))
    print("find bibtex from Google Scholar: ", len(success_bibtexs_google))
    print("not find: ", len(failed_results))

Bibliographyraw.txt里面是需要查询的文件
例如：
J. Hu, L. Shen, S. Albanie, G. Sun, and A. Vedaldi, “Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks.” arXiv, Jan. 12, 2019. doi: 10.48550/arXiv.1810.12348.
X. Wang, R. Girshick, A. Gupta, and K. He, “Non-local Neural Networks.” arXiv, Apr. 13, 2018. doi: 10.48550/arXiv.1711.07971.
------------------

success_bibtexs_crossref, failed_results = get_bibtex_from_crossref.get_bibtexs(raws)
返回的第一个参数为bibtex列表，第二个为没有查询到的原文献

success_bibtexs_google, failed_results = get_bibtex_from_google_scholar.get_bibtexs(failed_results)
将没有查到的文献继续使用google API查询，一般都是可以查询到了，没有文献在google scholar查询不到了吧

提示，这里返回的其实是APA格式的，在上面初始化指定，也有一个参数可以设置返回bibtex格式，例如
get_bibtex_from_google_scholar = GetBibTexFromGoogleScholar(google_scholar_api_key, GetBibTexFromGoogleScholar.APA, flag = True)
但是需要设置代理服务器，例如：
import os
import re
import requests
os.environ["http_proxy"]="127.0.0.1:7890"
os.environ["https_proxy"]="127.0.0.1:7890"

get_bibtex() 去掉s就可以了 

from apiModels.get_bibtex_from_dblp import GetBibTexFromDBLP

现在提供一个封装好的类提供使用，这个方法已经封装好了Crosref和DBLP的API
from apiModels.workflow.crossref2dblp import Crossref2Dblp

使用方法（无google scholar API）
crossref2dblp = Crossref2Dblp("your email", "inputfile/Bibliographyraw.txt", "outputfile/Bibliography.txt")
crossref2dblp.running()
坐等运行完成

（有了google scholar API）
from apiModels.workflow.crossref2dblp import Crossref2Dblp
from apiModels.get_bibtex_from_google_scholar import GetBibTexFromGoogleScholar
get_bibtex_from_google_scholar = GetBibTexFromGoogleScholar(api_key="your api key")
在最后面参数加上你封装的API
crossref2dblp = Crossref2Dblp("[email protected]", "inputfile/Bibliographyraw.txt", "outputfile/Bibliography.txt",get_bibtex_from_google_scholar)
crossref2dblp.running()
坐等运行完成

或者你想自己定义api之间的调用顺序
from apiModels.workflow.make_workflow import MakeWorkflow
from apiModels.get_bibtex_from_google_scholar import GetBibTexFromGoogleScholar
from apiModels.get_bibtex_from_crossref import GetBibTex

get_bibtex_from_google_scholar = GetBibTexFromGoogleScholar(api_key="your api key")
get_bibtex_from_crossref = GetBibTex("[email protected]")
make_workflow = MakeWorkflow("inputfile/Bibliographyraw.txt", "outputfile/Bibliography.txt", get_bibtex_from_google_scholar, get_bibtex_from_crossref)
make_workflow.running()

使用之前: 
pip install get_bibtex = 1.1.0