Merge branch 'release/0.3.0'

README

@@ -1,5 +1,5 @@
-SciHub to PDF
-=============
+SciHub to PDF(Beta)
+===================
 
 Description
 -----------
@@ -36,7 +36,14 @@ Given a title...
 
 ::
 
-    $ sci2bib --title An useful paper
+    $ scihub2pdf --title An useful paper
+
+Arxiv...
+
+::
+
+    $ scihub2pdf arxiv:0901.2686
+    $ scihub2pdf --title arxiv:Periodic table for topological insulators
 
 Location folder as argument
 
@@ -64,3 +71,49 @@ Libgen
 -  No CAPTCHA
 -  Slow
 
+Download from list of items
+---------------------------
+
+Given a text file like
+
+::
+
+    10.1038/s41524-017-0032-0
+    10.1063/1.3149495
+    .....
+
+download all pdf's
+
+::
+
+    $ scihub2pdf -i dois.txt --txt
+
+Given a text file like
+
+::
+
+    Some Title 1 
+    Some Title 2 
+    .....
+
+download all pdf's
+
+::
+
+    $ scihub2pdf -i titles.txt --txt --title
+
+Given a text file like
+
+::
+
+    arXiv:1708.06891
+    arXiv:1708.06071
+    arXiv:1708.05948
+    .....
+
+download all pdf's
+
+::
+
+    $ scihub2pdf -i arxiv_ids.txt --txt 
+

README.md

@@ -61,16 +61,39 @@ $ scihub2pdf -i input.bib --uselibgen
 - No CAPTCHA
 - Slow
 
-## Using bibcure modules
+## Download from list of items
 
 Given a text file like
+
 ```
+10.1038/s41524-017-0032-0
 10.1063/1.3149495
-10.7717/peerj.3714
 .....
 ```
 download all pdf's
 ```
-$ doi2bib -i input_dois.txt > refs.bib
-$ scihub2pdf -i refs.bib
+$ scihub2pdf -i dois.txt --txt
+```
+Given a text file like
+
+```
+Some Title 1 
+Some Title 2 
+.....
+```
+download all pdf's
+```
+$ scihub2pdf -i titles.txt --txt --title
+```
+Given a text file like
+
+```
+arXiv:1708.06891
+arXiv:1708.06071
+arXiv:1708.05948
+.....
+```
+download all pdf's
+```
+$ scihub2pdf -i arxiv_ids.txt --txt 
 ```

scihub2pdf/__init__.py

@@ -1,2 +1,2 @@
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"

scihub2pdf/bin/scihub2pdf

@@ -8,7 +8,7 @@ import textwrap
 # from sci2pdf.libgen import download_from_title
 from scihub2pdf.scihub import download_pdf_from_bibs, download_from_doi
 from scihub2pdf.scihub import download_from_title, download_from_arxiv
-
+import re
 
 
 def main():
@@ -39,6 +39,42 @@ def main():
 
         $ scihub2pdf --title arxiv:Periodic table for topological insulators
 
+        ## Download from list of items
+
+        Given a text file like
+
+        ```
+        10.1038/s41524-017-0032-0
+        10.1063/1.3149495
+        .....
+        ```
+        download all pdf's
+        ```
+        $ scihub2pdf -i dois.txt --txt
+        ```
+        Given a text file like
+
+        ```
+        Some Title 1
+        Some Title 2
+        .....
+        ```
+        download all pdf's
+        ```
+        $ scihub2pdf -i titles.txt --txt --title
+        ```
+        Given a text file like
+
+        ```
+        arXiv:1708.06891
+        arXiv:1708.06071
+        arXiv:1708.05948
+        .....
+        ```
+        download all pdf's
+        ```
+        $ scihub2pdf -i arxiv_ids.txt --txt
+        ```
        -----------------------------------------------------
             @author: Bruno Messias
             @email: [email protected]
@@ -48,6 +84,7 @@ def main():
     )
     parser.add_argument(
         "--input", "-i",
+        dest="inputfile",
         type=argparse.FileType("r"),
         help="bibtex input file"
     )
@@ -67,13 +104,20 @@ def main():
         "--location", "-l",
         help="folder, ex: -l 'folder/'"
     )
+    parser.add_argument(
+        "--txt",
+        action="store_true",
+        help="Just create a file with DOI's or titles"
+    )
 
     parser.set_defaults(title=False)
     parser.set_defaults(uselibgen=False)
+    parser.set_defaults(txt=False)
     parser.set_defaults(location="")
 
     args = parser.parse_known_args()
     title_search = args[0].title
+    is_txt = args[0].txt
     use_libgen = args[0].uselibgen
     inline_search = len(args[1]) > 0
     location = args[0].location
@@ -85,7 +129,7 @@ def main():
 
     if inline_search:
         value = " ".join(args[1])
-        is_arxiv = value.startswith("arxiv:")
+        is_arxiv = bool(re.match("arxiv:", value, re.I))
         if is_arxiv:
             field = "ti" if title_search else "id"
             download_from_arxiv(value, field, location)
@@ -94,13 +138,27 @@ def main():
         else:
             download_from_doi(value, location, use_libgen)
     else:
-        bibtex = bibtexparser.loads(args[0].input.read())
-        bibs = bibtex.entries
-        if len(bibs) == 0:
-            print("Input File is empty or corrupted.")
-            sys.exit(1)
+        if is_txt:
+            file_values = args[0].inputfile.read()
+            for value in file_values.split("\n"):
+                is_arxiv = bool(re.match("arxiv:", value, re.I))
+                if value != "":
+                    if is_arxiv:
+                        field = "ti" if title_search else "id"
+                        download_from_arxiv(value, field, location)
+                    elif title_search:
+                        download_from_title(value, location, use_libgen)
+                    else:
+                        download_from_doi(value, location, use_libgen)
+
+        else:
+            bibtex = bibtexparser.loads(args[0].inputfile.read())
+            bibs = bibtex.entries
+            if len(bibs) == 0:
+                print("Input File is empty or corrupted.")
+                sys.exit(1)
 
-        download_pdf_from_bibs(bibs, location, use_libgen)
+            download_pdf_from_bibs(bibs, location, use_libgen)
 
 
 if __name__ == "__main__":

scihub2pdf/scihub.py

@@ -214,8 +214,8 @@ def download_from_title(title, location="", use_libgen=False):
 
 
 def download_from_arxiv(value, field="id", location=""):
-
-    value = re.sub("arxiv\:", "", value)
+    print("Downloading...", value)
+    value = re.sub("arxiv\:", "", value, flags=re.I)
     found, pdf_link = get_arxiv_pdf_link(value, field)
     if found and pdf_link is not None:
         bib = {}
@@ -226,5 +226,4 @@ def download_from_arxiv(value, field="id", location=""):
         s = requests.Session()
         download_pdf(bib, s)
     else:
-        print("Arxiv not found.")
-
+        print(value, ": Arxiv not found.")

setup.py

@@ -6,7 +6,7 @@
 
 setup(
     name="scihub2pdf",
-    version="0.2.0",
+    version="0.3.0",
     packages = find_packages(exclude=["build",]),
     scripts=["scihub2pdf/bin/scihub2pdf"],
     long_description = README_TEXT,
@@ -22,7 +22,7 @@
     description="Downloads pdfs via a DOI number(or arxivId), article title or a bibtex file, sci-hub",
     author="Bruno Messias",
     author_email="[email protected]",
-    download_url="https://github.com/bibcure/scihub2pdf/archive/0.2.0.tar.gz",
+    download_url="https://github.com/bibcure/scihub2pdf/archive/0.3.0.tar.gz",
     keywords=["bibtex", "sci-hub", "libgen", "doi",  "science","scientific-journals"],
 
     classifiers=[