fixed windows path problem

build/lib/easy_literature/arxiv.py

@@ -168,8 +168,6 @@ def get_info_by_title(self, title, field='ti'):
     arxiv_info.set_proxy_handler(proxy="127.0.1:1123")
 
     bib_arxiv = arxiv_info.get_info_by_arxivid(arxivId)
-    # bib_title = arxiv_info.get_info_by_title(title)
 
     print(bib_arxiv)
-    print("\n")
-    # print(bib_title)
+    print("\n")

build/lib/easy_literature/downloads.py

@@ -1,6 +1,7 @@
 import logging
 import re 
-import os 
+import os
+import platform
 
 from .arxiv import arxivInfo
 from .crossref import crossrefInfo
@@ -107,11 +108,17 @@ def get_paper_pdf_from_paperid(paper_id, path, proxy=None, direct_url=None):
     else:
         content = pdf_downloader.get_pdf_from_sci_hub(paper_id)
     try:
-        if not os.path.exists(path.rsplit("/", 1)[0]):
-            os.makedirs(path.rsplit("/", 1)[0])
+        system = platform.system()
+        if system == 'Windows':
+            path = path.replace("/", "\\")
+            pdf_dir = path.rsplit("\\", 1)[0]
+        else:
+            pdf_dir = path.rsplit("/", 1)[0]
+        if not os.path.exists(pdf_dir):
+            os.makedirs(pdf_dir)
         pdf_downloader._save(content['pdf'], path)
     except:
-        pass 
+        pass
 
 
 

build/lib/easy_literature/easyliter.py

@@ -66,7 +66,6 @@ def file_update(input_path, output_path, proxy, paper_recognizer, gproxy_mode):
 
     replace_dict =  get_bib_and_pdf(input_path, output_path,
                                     proxy, paper_recognizer, gproxy_mode)
-    # logger.info(replace_dict)
 
     if replace_dict:
         note_modified(paper_recognizer, input_path, **replace_dict)
@@ -133,7 +132,6 @@ def main():
 
             matched_numb += len(matched_pdfs)
 
-            # os.path.relpath(pdf_path, note_file).split('/',1)[-1]
             replace_paths_dict = {}
             for matched in matched_pdfs:
                 replaced_str = os.path.relpath(pdf_paths_dict[matched], md_file).split('/',1)[-1]

build/lib/easy_literature/utils.py

@@ -122,16 +122,17 @@ def get_update_content(m, note_file, pdfs_path, proxy, gproxy_mode):
                 pdf_name = re.sub(r'[\n\t\r]', '', pdf_name)
                 # remove multiple blank spaces
                 pdf_name = re.sub(r' +', ' ', pdf_name)
+                pdf_name = re.sub(r'[.]', '', pdf_name)
 
                 pdf_name = '_'.join(pdf_name.split(' ')) + '.pdf'
 
                 # remove the special characters in the pdf name: / \ : * ? " < > |
                 pdf_name = re.sub(r'[\\/:*?"<>|]', '', pdf_name)
                 pdf_path = os.path.join(pdfs_path, pdf_name)
 
+                logger.info(f"The pdf path to be saved: {pdf_path}")
                 if pdf:
                     id_type = classify(literature_id)
-                    # logger.info(f"the literid: {literature_id}; classified as: {id_type}")
                     if id_type == "title":
                         for pattern_str in [r'10\.(?!1101)[0-9]{4}/', r'10\.1101/', r'[0-9]{2}[0-1][0-9]\.[0-9]{3,}', r'.*/[0-9]{2}[0-1][0-9]{4}']:
                             res = re.search(pattern_str, bib['url'])  # search for the arxiv id in the url
@@ -151,17 +152,17 @@ def get_update_content(m, note_file, pdfs_path, proxy, gproxy_mode):
                             get_paper_pdf_from_paperid(literature_id, pdf_path, direct_url=bib['pdf_link'], proxy=proxy)
                             if not os.path.exists(pdf_path):
                                 get_paper_pdf_from_paperid(literature_id, pdf_path, proxy=proxy)
-                # logger.info(bib['journal'])
                 if os.path.exists(pdf_path):
                     replaced_literature = "- **{}**. {} et.al. **{}**, **{}**, **Number of Citations: **{}, ([pdf]({}))([link]({})).".format(
                                         bib['title'], bib["author"].split(" and ")[0], bib['journal'], 
                                         bib['year'], bib['cited_count'], os.path.relpath(pdf_path, note_file).split('/',1)[-1], 
                                         bib['url'])
                 else:
-                    replaced_literature = "- **{}**. {} et.al. **{}**, **{}**, **Number of Citations: **{}, ([link]({})).".format(
-                                        bib['title'], bib["author"].split(" and ")[0], bib['journal'], 
-                                        bib['year'], bib['cited_count'], f'{pdfs_path}/your_pdf_name.pdf', bib['url']
-                                        )
+                    logger.info("Can not find a downloading source for literature id {}. You may need to manually download this paper, a template has been generated in the markdown file. Put the pdf file in the folder you specified just now and add its name in the '(pdf)' of your markdown entry.".format(literature_id))
+                    replaced_literature = "- **{}**. {} et.al. **{}**, **{}**, **Number of Citations: **{}, ([pdf]({}))([link]({})).".format(
+                                            bib['title'], bib["author"].split(" and ")[0], bib['journal'], 
+                                            bib['year'], bib['cited_count'], f'{pdfs_path}/your_pdf_name.pdf', bib['url']
+                                            )
                 replace_dict[literature] = replaced_literature
             except:
 

easy_literature/downloads.py

@@ -110,14 +110,15 @@ def get_paper_pdf_from_paperid(paper_id, path, proxy=None, direct_url=None):
     try:
         system = platform.system()
         if system == 'Windows':
+            path = path.replace("/", "\\")
             pdf_dir = path.rsplit("\\", 1)[0]
         else:
             pdf_dir = path.rsplit("/", 1)[0]
         if not os.path.exists(pdf_dir):
             os.makedirs(pdf_dir)
         pdf_downloader._save(content['pdf'], path)
     except:
-        pass 
+        pass
 
 
 

easyliter.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: easyliter
-Version: 1.0.3
+Version: 1.0.5
 Summary: EasyLiterature is a opensourced, Python-based command line tool for automatic literature management. Simply list the paper titles (or ids) you want to read in a markdown file and it will automatically collect and refine its information in the markdown file, download the pdf to your local machine, and link the pdf to your paper in the markdown file. You can forever keep your notes within the pdfs and mds on your local machine or cloud driver.
 Home-page: https://github.com/Psycoy/EasyLiterature
 Author: Oliver

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="easyliter",
-    version="1.0.3",
+    version="1.0.5",
     description="EasyLiterature is a opensourced, Python-based command line tool for automatic literature management. Simply list the paper titles (or ids) you want to read in a markdown file and it will automatically collect and refine its information in the markdown file, download the pdf to your local machine, and link the pdf to your paper in the markdown file. You can forever keep your notes within the pdfs and mds on your local machine or cloud driver.",
     long_description=README_MD,
     long_description_content_type='text/markdown',