From a07147ed5c6832ffaf6ad57ff03470d3c496a734 Mon Sep 17 00:00:00 2001
From: Florian Jochens <fj@andaco.de>
Date: Mon, 22 Nov 2021 09:37:41 +0100
Subject: [PATCH] added updated input files
---
example_input.py | 14 ++
input/README.md | 26 ++-
input/__init__.py | 6 +
input/__pycache__/__init__.cpython-39.pyc | Bin 0 -> 290 bytes
input/__pycache__/interface.cpython-39.pyc | Bin 0 -> 2292 bytes
input/__pycache__/publication.cpython-39.pyc | Bin 0 -> 5659 bytes
input/get/__init__.py | 7 +
input/get/__pycache__/__init__.cpython-39.pyc | Bin 0 -> 350 bytes
input/get/__pycache__/acs.cpython-39.pyc | Bin 0 -> 3164 bytes
.../journal_fetcher.cpython-39.pyc | Bin 0 -> 2224 bytes
input/get/__pycache__/nature.cpython-39.pyc | Bin 0 -> 1757 bytes
.../publication_interface.cpython-39.pyc | Bin 0 -> 2041 bytes
input/get/acs.py | 105 ++++++++++
input/get/acs_fj.py | 100 ++++++++++
input/get/journal_fetcher.py | 60 ++++++
input/get/nature.py | 63 ++++++
input/get/template_.py | 52 +++++
input/interface.py | 77 ++++++++
input/publication.py | 183 ++++++++++++++++++
input/requirements.txt | 2 +
input/tempdir/input_fj.py | 144 ++++++++++++++
input/{ => tempdir}/pub.py | 0
input/tempdir/test.py | 15 ++
input/test_doi.txt | 4 +
input/test_input_get_publication.py | 28 +++
input_old/README.md | 3 +
.../__pycache__/input_fj.cpython-39.pyc | Bin
{input => input_old}/example_urls | 0
input_old/input_fj.py | 154 +++++++++++++++
input_old/pub.py | 32 +++
{input => input_old}/test.py | 0
{input => input_old}/x | 0
32 files changed, 1074 insertions(+), 1 deletion(-)
create mode 100755 example_input.py
create mode 100644 input/__init__.py
create mode 100644 input/__pycache__/__init__.cpython-39.pyc
create mode 100644 input/__pycache__/interface.cpython-39.pyc
create mode 100644 input/__pycache__/publication.cpython-39.pyc
create mode 100755 input/get/__init__.py
create mode 100644 input/get/__pycache__/__init__.cpython-39.pyc
create mode 100644 input/get/__pycache__/acs.cpython-39.pyc
create mode 100644 input/get/__pycache__/journal_fetcher.cpython-39.pyc
create mode 100644 input/get/__pycache__/nature.cpython-39.pyc
create mode 100644 input/get/__pycache__/publication_interface.cpython-39.pyc
create mode 100755 input/get/acs.py
create mode 100755 input/get/acs_fj.py
create mode 100755 input/get/journal_fetcher.py
create mode 100755 input/get/nature.py
create mode 100755 input/get/template_.py
create mode 100755 input/interface.py
create mode 100755 input/publication.py
create mode 100644 input/requirements.txt
create mode 100755 input/tempdir/input_fj.py
rename input/{ => tempdir}/pub.py (100%)
create mode 100755 input/tempdir/test.py
create mode 100644 input/test_doi.txt
create mode 100755 input/test_input_get_publication.py
create mode 100644 input_old/README.md
rename {input => input_old}/__pycache__/input_fj.cpython-39.pyc (100%)
rename {input => input_old}/example_urls (100%)
create mode 100755 input_old/input_fj.py
create mode 100644 input_old/pub.py
rename {input => input_old}/test.py (100%)
rename {input => input_old}/x (100%)
diff --git a/example_input.py b/example_input.py
new file mode 100755
index 0000000..a8331cb
--- /dev/null
+++ b/example_input.py
@@ -0,0 +1,14 @@
+#!/usr/bin/env python3
+
+from input.interface import InputInterface
+import input.publication
+
+def main(url: str):
+ #print(get_publication(url))
+ print(InputInterface.get_publication(url))
+ #pub.print_pub()
+
+if __name__ == "__main__":
+ #main("https://doi.org/10.1021/acs.jcim.1c00203")
+ #main("https://doi.org/10.1021/acs.jcim.1c00917")
+ main("https://doi.org/10.1021/acs.jcim.5b00332")
diff --git a/input/README.md b/input/README.md
index 76bd11d..0ebd7e1 100644
--- a/input/README.md
+++ b/input/README.md
@@ -1,3 +1,27 @@
# Projekt CiS-Projekt 2021/22
-Input-Skripts
+Input-Package to fetch publication information with a given url.
+
+## Usage/Examples
+
+```python
+from input.interface import get_publication
+from input.publication import Publication
+
+def main(url):
+ try:
+ pub = get_publication(url)
+ except Exception as error:
+ raise error
+
+ print(pub)
+ pub.title = "Cool new Title"
+ print(pub)
+
+if __name__=="__main__":
+ main("https://doi.org/10.1021/acs.chemrev.8b00728")
+```
+## Authors
+- Florian Jochens
+- Sam Ockenden
+- Julius Schenk
\ No newline at end of file
diff --git a/input/__init__.py b/input/__init__.py
new file mode 100644
index 0000000..428d906
--- /dev/null
+++ b/input/__init__.py
@@ -0,0 +1,6 @@
+"""
+init.py for Input-Package.
+"""
+
+from input.publication import Publication
+from input.interface import InputInterface
diff --git a/input/__pycache__/__init__.cpython-39.pyc b/input/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c120e069d340aff9e417dc18dfa02e8284e91486
GIT binary patch
literal 290
zcmYe~<>g{vU|=}ZIW4h@fq~&Mh=Yuo7#J8F7#J9e6&M&8QW&BbQW#U1au{=&qL>&#
zY~~#1T$U&nMurrYU<OUrDp{_~yv!24f=Y$7{2~R<yn@ma-GId8?8Nj`Jq50pAfq)I
zZ*d2dCgo%%CzfR9=V>zD;sdMm%qvMPN=r;m_0wd%#U3A@lAjzOe@ieEWQJY=LPHVA
zO}F?V;+Zf_Ma&Eg3@aIm*clig#4kPljQreG{j@CoqSS)?Vtud%-GZY0tkmoh2v0vg
i9^~Bkc)fzkTO2mI`6;D2sdkJY|FSSJFtD)jFaiLI>`t8k
literal 0
HcmV?d00001
diff --git a/input/__pycache__/interface.cpython-39.pyc b/input/__pycache__/interface.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..845c6597fc1a11f6533754364429af32ba2ae9aa
GIT binary patch
literal 2292
zcmYe~<>g{vU|=}ZIW2J~7X!m%5C<7EGcYhXFfcF_yD=~@q%cG=q%fv1<uK+lMKLjg
z*vvW1QOqffDa<)6Q7mAZHHtNbF@+_EEtfrtosq$vA%!)Ct%V_lt(hr`BZWDbL6f~I
zipw*vB(*3lF*#KsEx$;iBqLS9Gq0euL^mKYIXf{uRUtnwr&6ILBePhcI3vF_Cq*GC
zRUt7sIkmVrHANw<C_h&rzqF({GbI(G2&zqwi|ZxG^_q;gSjrP~vi&p}Z*d2dCgo%%
zCzfR9=Ou$AkueL*dln1~45<uJj42FJOeu^}%qdJ!Ea?nUtf_3N?5P|n%yXDhSW;M9
zSehB5I8)hD*izVA7@8TQxKfyc88kU=@qt|r_f(Y=mx6+VLU3kYdQNIdex5>kMrLw`
zLP}*`Vs2(~Vopw_LS}A3eo;xWLSkNuLT+MSVtQ(^LRxA`az<)VF<7&oCetnE(xRMO
zY(=RhrA2wkj7Sb=VqjnZx!oBQH6aWP3?&R%jOh&7Ohq~+3=5bRGB6^GFsCpsU@2k9
zVqM7C%-F;TQtQGHD^tr@!?=L0hG8LNkx>of0(KCKiGh(Jn4!=J>@Vi3S74`r{1TFp
zs*nkbG~L|Pl8pQmg_3-Q^wbiCL<OWU*3HZ-E=kNwPUV8@4M;3X%uOwU`3z*7E*!vB
zSrvekDU=rFSb+$T;V1?p6qZyLq=J-KDHN9!A%r2}WQFV)1(;(L@{1Jw^7B#^GSd|D
z@=FwoOAA2ZpPB;KUZv@muTWf&nw*)InXKRjjS7YGjMO4fA}!5JQAjMYQc$n1Rrk~6
zC<2B4Eq-W>#V6+^78j=$-x5wwEr~}L<Z~=3DauSLElG7PD#|aq#g>*|l$%&`ivy&%
zAh9GPiaR+mFTS)mH69e-{9s{3qSa(7Vr5`pxW$WN?n;ItJ_ZJcU;6qP`MIh3X<7P3
zsRjAP`kCNtR8W+km6}}w;pxNUO|PJ`h=+lJK@^m1L_q0@hl`Pek&BUyk>x)d3l}37
zqX2W29BN|LLvs&GCISTmHv<C$I3Y?gGBBhtE?_8OT)<SqypS=AWdZ9#hJ}nJZ1L>r
z47Cg;93`A3Y+3Bhj44bhOz8}1%*{+G%#sW)46$;xj3rzPxKmha7#A|7FqJYEnbj~X
z;HhC;$jHc0Xja3J&XCPqR8+#7!n%MVg>3;JD6xW)Gb2L{NdLTA#;Uv${sjUl><bub
zK<0C_GD$KlWL(Ht%Ty&+!j>htfTxCOflvx3NQ{vooFUJOg`q^a@(CkDEi)rSl~M_B
z3Ky#0W=4>@NQM-qTIM?DJT3@rz+k`-&QMqe(mjE(QizcO1WQCxxY2btF-9^JmKiV<
zmVvVqPt{6zY70(HEK1HuEmp|PQ&3M&Em7A2rOXm=VoNMaRfta1t%}vsE2vb+%}*)K
zNi9~;z(|{#aMM7ANJ&v<YB4C&KuQ)+nVPEyR}q|81}b3kLCF|qBFJi3no7&eNi9}K
zsIOwHuGLRZE%AE^Dr%}Y!S2!4E2ylJb^{xdmY<W8U!IwluHXxCpp`;(Z55M_LKP1<
z34&6MUUluuzyJULk79>rrz&lTVsI`}NXbtv24}{M#IjU{L<M!IDs^3OcB+y`R-Bxe
z2UeSu3N1QQQ#3`3K$X`mc2FM5$xOP%5|CJuaf>599^{+&_*-lRiAAY-B~k1}sm1v@
zWvSpyTLen3w^;I0D@uw$e!Im~lzNLbH?br+;}%<DK|yL>$}QG{qRhOKTP#`mnR&N3
zApr`qfEU7yhlF4eJ1AQU#K)(nmL$TmczpaVPS=X$)B;d_bBo&(T+D;>y(UYP5OQ$G
z=OyN*7T;n4Ikt!wWE5*EsC)qDYY4&5z`#(%!N9;^0LrimpbX0?!OX%a$0)$a!^FWT
z!py<Q#3;eY#3;td$7sOF$5^F=CG)~;1qW+tu_iYtj6k->$KT?Lhx#Ty{uWPsd|_!~
z4pfFcK0YNsIX)g7U=Y9Z6qh8HWF|vO|69z(B}GM`1_HQD0lO38Y*4`jVSzmWDkDJt
zD+Y;kFtV_)FtRW)F$zgBF@j@6le0(-<b9_6VsMNU$$-2q1R}&i;)0L_Re&fGA-00d
ig;)bJ7{UTsc#FdZ5<zw##}$JLJQfxnMh-CKVFCcf_jcI;
literal 0
HcmV?d00001
diff --git a/input/__pycache__/publication.cpython-39.pyc b/input/__pycache__/publication.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..ecb94eef74276d09e4ce203ffd67d6033002ae8a
GIT binary patch
literal 5659
zcmYe~<>g{vU|=}ZIW2LvBm=`^5C<7EGcYhXFfcF_>oG7exHF_Mq%gKHq%bx!MS*xs
zDa<VlDa_4GQH<^kDJ&_hEet8F%}h~DDQv+En(WEQCV|-8Fw?3S7#LC+q8L*cqL@+`
zqnJ|!Q(54UHI+q@A(btaHI-eG0YauQ&*21{&l<&%%96r1hcSgcg`<TfiZhifg)@b#
zg`t@-iaUh~EW@3`)4~$PlgbO`@uu*#utf2t@TUm0FhudEFa<Mc3f<xkC{4=AOinDx
z%+IS*=Td-zpwxn*)Z)~<l46BK1tcZKU=@CvoVVCh@-yR0i*jzUmSmRXq~795&d)0;
z%1kOP$uBCt#h#U4T9lWVb4#EAVSao{VoB;Pj^fg!tkmR^;#<6VrMdCRnI&M$i*Ioi
zrKY78rRF847T@B83nzo)1r%ru3=AMP69WT-Gbkns7#J987;6~f8ETkn7~&agm}?l~
znQB;S7~+|0SZf&KS!&p77~)xLI8qo(8H!BO8EP2f+49(GI6!m_Cs@=AEXtn8R>N7t
z5YJx24i-%-;izHAVs8eS&Y8zn!(PJ>&zZs)%%I7XxQmH_0UQdTpbAJVO3Y0yNiBi|
z3`j^94&bV+3P8#fpdn@jV<_aODU@WSDj)?BLQ6?yK`Kn4l|pez5kd-L8aUXk6u=Z=
zlfcTbnu8o~Rymo)B_P8Rb8-}rB@mW_-GwY=r2x_t9g9!`aUa-M#Tlt7Rtlha2bo%w
znv<GXoQhBhHVjE27H`5*ixoJipgfRappZjKnP`SW6&6EXS6otr;Xp)kgP83MO^FKS
z8JWo$3Yo<UNvWxM3UFm93Q3g;B^jB;$QeQb&0e@_n9YfKl^8a|6E{|i5k_FxhGrR(
zIp8=zwW}z#q_il{O2IEb4-w>knp{Po98?4<(27_X7#NCJK?EC!U<VPLAOe)pZZYSi
z<`r=;FfeFx-C`+D%}FDm6Qr~Vu6-p#5ibJ+!!JYqjQreG{j@CoqSS)?V*Sj#g3=P*
zf};Ga)a()nPam8FlELMGUP0w8j`;Y@yv&mLc#wmN<v^KVoQ)9yIT$&Z*cf3XA5)bG
zQbN#!X<o^AiwzP6$&4T)pcusFgOwpZ3=9k@j0+fQ7_t~^7_yjBm=-YCFl4bT1o2pF
z7_!))BJ2wpQ<y<=3qU0U=R!slJ{O3;kRzBulf|#9D+E*^T7k*}5U#G}a>>usEiKA{
z3RTx~IhK}W<QEkq1iT={B|-q~AyDp7$j`G<sIKJ-hL)NTCDpZDLGaQNB*ax+%LPlo
z5OYByznF9sZZUFca^GT0%P-1JEP+HjC;{AJ$;!{n!<GVW38$x)z{}<M;*z4wymX{^
zWh~+WB@s~Mf@8P{6q>i#<3TFp<BdQ?Gf0Gik%dEuk%N(oQGik4OO-I#N6<Kiszr$x
zP=W*{MR3^;s%2{!(iyUuiuh6((;0&q(iv(QYZzP@Vufm%YCti@w19CT!$L+zhC;C#
zaLMd<iv^U_HJNU)B^DH<=A{%#fYL5=5hyW7@xw9;$eEdW>9;sw0uWDty#sQ0kr)F5
zgCocnAa61-aWJwmu`qHl3NTj5Bl`hMASHtW7Mjc$K>h*cDzJab7#J8z7-|@s8B0KQ
zkrXJcEnu!;1i3#i3@XD?%1{(n!|1{gYf#Hn!cfBmRqX*)%>+_is8zz6!nlA9BEOKa
znX!qnP%BReF3Q-<2oVM80@qk<j7T+>BRFV4)jFui02QS0WTTK@qyXb6l;kUbvb-KF
zl#2DZ;H3||)`N@Stn*;ntq>;X7b(EgF35iT1vz#DKyHtQxfQ8=h2(cDG^fLzS!Ewz
zjFh$&QY#8llS_)>ZYu@_fe*9}gc)C~qmY+hVx^#7U8}Ciev1WEY2D(0$%0c?krV?1
z!z~t&t8Q_IR2HPV78T_e6^TI7A1ECaNi#4oM6rOf6?%FDB~NcqdIK54z{SJJ$IQdX
z!N|kN$Hd0S_MeLxM6xkgi6W;ySg;hMq&ZOf17UEQ16f<cki}5Ln8lC{YV9#r87MgC
z=N2Rur51y0)6%@m!curE0~{CS`N*|fu_hz9%-3WB=lNT#`6U^tMQ9$l#TFl*S{NUn
z2J!>Qb_S*@A!N5gq){?ENExUR40h--aOOw>6}gPF8B&-)33oO_3aB7vp3RWLGMBxX
zkr9-A7_wMWSX0<C8T-Ke6ofb{k~kZr>6XHg%~G_h1jggcW-2NuVMyTunUyD0!jQrZ
zQa76+g=a1^NUVk-i^GK>R<D+^gdv5uhA|7|7QPzBEY8^sDf~5zS*)`eQUq!kvp{YV
zoXZK)Q`nKmQNoZS1Y)N!1T$y~`&9`!7L{Zs=cGbfW>%moph}nvDLlZ<AuEL{VJ;Vc
zPu<WUAFvvbIt7I)ZZ1Sge~Y;|wV+6dfq|ilkINaUd2RI)RLHyp)nrwcTp^$)2~rIT
zYPlq5mZU=4E2#=;`8hfH<(YZu$SqAPt|}c;v{vyW>n^t9suBigE7ZykDu`O0K?PBK
z0P;S_%cwz6B?vYXBmu)!7Fb=GmtUd)_he#Tr2;r*B0Et}lj|01K~ZKNw9*5W#o)wT
z1Zq`)E52LIAX#v;1(XTFEg@)92j^Gxgw6>zF20~NDGQX=L6sB(BM&3Xe-<W|e_X5r
zpjv{7kCBg&i%E!)i;)E?!@|t+mxYDp4<9>f9)_Ey$?WInrzrqx_v9t!rpCwL;);*Y
z%}*)K0kL`F;|og@bD%Qp@$o77$?@^Gn2Sq_ia>3nA~jIq!<?8`S;P;jm_fDPEuLaf
zw<<X|wIm}y1ze?p3#wZzN%{FXMT#JG>L3DK?I8$o1qe!4pxUcghJk^BgOP=mfsx@a
z8zT!N7bDMK9&J8;CPpq!K50IdB9Kaq&Mhc-!ChrD<jyTeDl-_eq%un~q%x;4&S6af
zb(>kESW}r(SmrQ-a&QYv6k7^=FoPy%ku0d}WQ9Z+$T8r^fy5f9=8gxI!pWdG1!V;g
z2C+fK3b;s70`(0+y+TM25li1N1>9yx>_@H};q}@u>CJ(AW}sr7^zIzC4pVYw2{_oT
z6oLy<lQYvYQ;QWc(~v83MEe1rkF7uv1<I;WtteeQSal6*x50JzX|f`ksfcJVG61Cr
zHgH9REm?r&(Q+&}L$rhPDky(52*SD$Rf4eU8{S(e5@29pK&hiZi5pahf)f-duOoL9
zpdAKK9R;elSU~&~rUl?G!$L-ISAf~CDulDTRu{E|tght(3A*HGA{F~kLDXUsDu`Na
zR@ZWYYXnVpaO(o%X>k4krF}?fiGngVxN9d4Vxi@3Q1LJi6eJ+OF)*^QaDaMJjC?<<
z1dsxyxTGjP-cOSeoDWyB7ioY@(gYD&AVLR3fD0dZk%JWUU>m_j2`Cr0!7SroX7~r{
zwlV$V5eJ)#QFMUX|KOqn)Qf<Pi-C&`=2UROk-|8K1zc>fU@bN{ZgIk!mYOWsQb{t%
z3Q%zY!XP#%*uXIiD(t`mNmz;uaNW-6r^$jXVQRACPLtq}02AQg00q`+P;h|i90q8Q
zwn_-@W&)`Zqzmj;P{^aDM&=Zz1)x;Ox{z@pOE7~bvtLy)A~1@vq(Zo@#k!cO5lIp=
zRU%2Er%p)XWP>D5lGEizMA(4RCExEVLAYId&`zUYks&DYfddsmfP)v5YF2@a04077
pMhUhekcgiqGq|DxCpoYPwxoKC!v<30+JRhM4604|>KR!0Q~-3+NjCrh
literal 0
HcmV?d00001
diff --git a/input/get/__init__.py b/input/get/__init__.py
new file mode 100755
index 0000000..2a6ddd0
--- /dev/null
+++ b/input/get/__init__.py
@@ -0,0 +1,7 @@
+#!/usr/bin/env python3
+"""
+__init__ for journalFetcher-module
+temp file with nothing in it right now
+"""
+from input.publication import Publication
+from input.get.journal_fetcher import JournalFetcher
diff --git a/input/get/__pycache__/__init__.cpython-39.pyc b/input/get/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..e6f5d85fed9093448393bae5028b8443ca4550c9
GIT binary patch
literal 350
zcmYe~<>g{vU|=}ZIW6%70|Ucj5C<7EF)%PVFfcF_D=;uHq%cG=q%fv1<uK+lMKLjg
z*vvW1xhzpEj0`C(!3>(LRo-0j@tJv<CGqhJY57G8S^1?!d5Jl0sU^u7sYSZE`6;D2
zsaz$gxdjSonK`Kn<(VZJ3VHb@8JT(M3YmEdnI#HEnduoN3VHeETrWWm(PX^E9Z;H-
zlbM`Yl9`{U$#{#;3&l`BP1alN@$o77$?@^G1T*srN=x(#5E_a=K8TWph^MEP=s}$n
zp9XPL5i<h=!%BuCHU<U=@ykd*BR@A)KP^kYD77HJSRbrax1cCLD>b_W!qZPrEzyU0
ZRIi}&7KaVQYjz;pidh&K7+6?%7y++lWxfCa
literal 0
HcmV?d00001
diff --git a/input/get/__pycache__/acs.cpython-39.pyc b/input/get/__pycache__/acs.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c0f9cbd06555179aaf5d113b3567d24f4d08bebf
GIT binary patch
literal 3164
zcmYe~<>g{vU|=}ZIW2Lu00YBg5C<8vFfcGUFfcF_+b}RNq%cG=q%fv1<uFDurZA>3
z=P>0mM=>*k#8`4za#^ETbJ?QU7#Z9dQdm>iS{PE;Qkk2Xqu5iJf*CZ~tGc<IGct2h
z6q0iii;ETV(-ge&ON;UnbKFu(k~30^xI&8)(^IV!oHJ6BvlTMa6hez~6p|D36p~UE
zN{drd6v{J8G8EL46Z7Iri&NuEi*nSt6d)imFGZmwBQ;MU4P=x;L1|J>W^!UlW_})2
zQ+jGiJd&t7*GrHm{WKYG@u50Glj#<B07CmM4(H4gutCWn4agWCGF}V}45<uJj42FJ
zOeu^}%qdLij8QD9tf_3N>?zE1m{M3$SX)?{8KXGBVw_+xwiI@-7*{H53P%cO3qvzw
z6n6?&FoP!dEp}*tR2hK%7hI5<oSBxHtN;~ONXst*`BuTvIanbJ5`@KiV5Lzkh6YB4
znoPHtON(-Du@$A3losVBGa@;giGhIu<Z@?FoJuh;FqAMXU`%1GVOYpi%UHvh!X(L1
z!j#2a#t_V)$y}8OHWd`cp~b1i3PGvqsTB$(`3k8OB}IwJB{16+ieXMHE=?*fDay=C
zFILFRQ*g=8gt!Z2LWsYMzm-C8X+c4LQHercK3H0}v?!+-Zb_B4Mn*|VL9xA+zP_ft
zMoNCBUVc$Jh-qk`rxBA<ZBnbLA5*Ta7Za?l`4Z#}O_p0sMX9$~a}!IFGm2Ol7#MB|
z1&0O%_y>i!y2N|=hX(mM`UGn-6|pfeFhp^Km8GVD(#}eTA|3_?hF`k+8Tq-X`e|AE
zMX3e(#rm0f1*Ijr1x5K;so5nEo_>02iGE^ov0g#tEpDXbCk_fjkSiG2co?gMq0ys<
zqyi=AWf>S4K$#63^fQ<sL0`kLkP#H{3z$+E7lMPomZ^rZmbr#$0aFSyL?ny3mIcgb
zf$~{uS<@M6*}!6~3mIJ)Vg+j1YuFaB*05)>EM#P4DD(o$vBA}IfcfljK4&^ZEf-jf
z10q(-UBkVADTNbi8cz+^0@fNHsA)4&m}+^`8EW}zm=`dma4lr4<*(sSXUJxrz*sb?
zh98t@7BHo7gZ1vI6{rzdz?8zXkP)haD}{Ff8%zwOHj8Be`$C2kz7+meCP{{cjCo8c
z0=0r*6@qYGdN4jj2Uv{|SWF16CJ4qyQX`zsP%8o!7Y4gWsFuA(1Q9Y57z<Ns_!h91
zaMTFa2-OJJh@^<5i1xCAL+wgBL#-&-k75fMYsG5Bz&>CqYN!zd*#P(Bv0CvOaY+1t
zRWKIaf$>4=vRJ^bl>m#0LtV>M!~o+XsgVSWNx;>p!1zdNq|zB`rNQEokhscXS-_bh
zwUDt^x<+~d*FuH`>?zU<8Ea)~WKv|ZnI|w6rPN3-V6Bk>`Kd+}>{p2z$r`B|=@eO*
zUnejY?kM4|VX0xQVXNV&;jH1R;jQ7T5pCuSX3&(YS_IFNkW^i)kWrGGqW~&rlZ#Rl
zOHzv!oKh1@GSf<Pit|egbTjjcOA_;vQ$e}DAh9SluLM%cBeFld6iY5H)-6s=EK1Hu
zEe025j?Tfl&_cKv#RjBu7;XW=z$$*d#G;bS<eb#_jMT)G)S@C#Iaei=7+sQCl9Oty
z<l^tC5E|s86kElkmyzR^lcE~}lBg1a@|^SYN{TX*97{_w@{6jt^pZ16birDy`1J}(
zlXO!OOHy^q5_3vZt0d5@(k)4>$j{5qt-QsUSjC&4qg<4lmRgjWmz-LBizz3wie0ZL
zHO(bIvq}hDo>}SZ!^*Pi+LxeG%I_A7Uw&R{m5`pFk8eEG9}wGbF=j%AlOYb&O)ttX
zEx5%Q1hYev@fJsNW=VWWWkG6{6v*AFDY_uVsd**w$w`&4DyvEZw;ZaSRqA+DLaP|v
zyu{qpDt$Z(Vcq~ar6@D0v?RZ%xQa<fp^8aQ;TA&?sHD{7DFW3%w>Ur*GAQNTVk=I~
zNlh-f#RjQ2Zn2c4R+QXgODrfz%}cq(mX=?Xn^<y-6(m~#HsTg*aY0UI$t~uB{DLB8
z1_lOAS#aroiv?s}6gP;3ridt>qSUl_P*8ycZ?UK3XM&3UTdd${zQu#=&?vS<a6-7n
z4)t#oC%C~-oROMxi=((SDJwO(q&SKP%8G}W2<6@4%`43XSp;q>6yM@Pq=zVe1RJa=
ziW4pn#SU^`N`59-EFSEtC~lA#%nbq{4ze?EaVA3>B*js@FecbsaGC(yAH@#xGT2xU
z18OXY2{#tRK{hr@6kQ}fC$YE$Ttz|%UQpf24~jN$us~Z^pc=3O)V$!}V&r3FVHRK%
zU}9n9W8`BJV1lw3`IuOkSs1w(xfq3*c>b#~GW};_=J_vzLWA@OFi9~X)S=2l)ibd$
ziZStl&5~i_VdVH<B@QW{iuBN2hS6LD6%OE<7nBTBK+PLQKZwsj%>X18*rPlpsl_Gn
z;MQbnQ98(%pk&LyR3!ql4_SeqCeJO7_;^qTiI2a<6(66QpHiBW8Xtd)CqBNgG%*J%
z!yX@>lAjzOU&IXxOrBy;%Q87PwIm}y<rZ^sNzpBqr2PDxB0dHN25`zQ(gv|~Km-;?
zf}1=1Ah!uHFfed1vaqr-F)<2pFfj_bF)@N=H93k5K)N|W_DO=9HlTpggQf$R2O)V<
r5F(Ehy%0x$0t{>#QXqky0}d$;8;ED^Kv}Vv1Jt}^<6z=p6krAb8vBSl
literal 0
HcmV?d00001
diff --git a/input/get/__pycache__/journal_fetcher.cpython-39.pyc b/input/get/__pycache__/journal_fetcher.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..40e849f122b4d16639be285ad011e0852d92f38e
GIT binary patch
literal 2224
zcmYe~<>g{vU|=}ZIW2Jm8w0~*5C<8vGB7YWFfcF_doeIDq%cG=q%fv1<uK+lMKR?v
zM=>*k_{=#hxvWvFU^Yt*TNGOgV+v~ydoD*52P1<!Lke38dkaGfdn!{3M=x^}X9`O&
zgC=K{GFL!iQEFa^LUK-Gaj`;Levv|PL27blT4u6>SAJ<xUSbZ{OOR7EnQpN=Iyw8M
zmL%TdOH3**DN0N($xSWE$WPH^yv6I3npj$rnO2$;oL^etr^$GWJD@ZvCo?&*Br`uR
z8Ds!5hWjUlfq@~FA&N1DA&M!5F^V~rC6zUmErn?gQwnnmOAAXgV-$NTODabyYbqyL
zlr@D7B-+dv#RV1T28*+&a6rX*K;kK!DO@cK&5X^AQM@VK!3>%_xA>smaZ4>p&PXk)
zGUHNEP*4cT$ShXKELKQVfcZ%m5fW(-r3$(EDWy57#b6DZOt+Xzi*jzU6{VJx7Ud-~
zBKeD%fq?-Ok<Or~@?l_LsNySOSio4ru#mBqF`OaKfQ6xiA&V)Cxzdi2p_Yk}p-QBL
zrG}}Qv57I9A(A15v6iWhDUS<68!#9!l(5z?X0fF(H8TY>Xfjtl1iJv_?4Z<=qRiB?
z)MAD5)TH9flvLe}lH44H#Jm&*h`T^OLWvXI%)H`~#JuEGF1R59iA9OIsU@jJ#a3`J
zT?BxOS(Q{4q$-pa<ya{cmlPp{3qblI;wkx=x}`-q3MKgpi3$aXm`5mvILk`GDK!zE
zP7rPa`3Z#ms<=TO(JM$SDo!oZWWU8xlv-GtT3k|mi#a{D<Q7+IMRIBZC`}bdae9P=
z1h^Iz<rm%J3a%_JNzHYw$Sf&hVPIg0Vo%P`D@n~O(PS=S2l1JUQVVY}rxq2hWGLce
zU|{%Vsh^Rbo2s9drC*d<kYB8ynO9I+qFYdupOu<j0^#YWr<UkvLGnO6G%4s6RNmr9
zPc4Zr&Mz$x1Vu9_z8Scg82K2580DC%#8Fe39!xDtIsv5_kTb#QM2LZbp@boY5t2?o
zX(0s?+tu*EbA)C$-L%rYWRT}U;hdDJkeOSMlbV~FSCX2dkeR1YT$%(<yLxbq&Kar6
z*~JQ(X$t9?WvO|fxKhZ;%*!qY8IY(@Tv||&Uj)((^(I_nl_jb_zy*VPb*;KWMq+VZ
z35w0?$%%RKrNyc7rA0X!n(BTlnQrkpmXs7_CY6??LgI%lEx#x?v1BD9I5xmB03rAp
z7#MDGBN?C!3R5Ofo?@?(LUn^4k}@)aGYjrH@`JM|HL)ZWl(mowH+UjO1bdY&s>|_)
z9w>z%<rq*17J*V$kq83=B(Wj|6+fD49i-rrL$wr~^pFh3D1<?w3{HVO&=iQ2_L3<N
ztkAs765W#2;u5g$OEOX+RSZ%nS))4GN+B4UfUzYqkV&vy2nr)j#v)M8frJexOG8-T
z1jU1_*c2&<q)~0uLssXf$#;t*K0YroH#I)~7FT>cq|}d(zr_<DUs#%$1C?Qqk59=@
z1_>9JB$i|*L+Zd=%*7=|;IgMk02FVas^At&Qht6;ktm1{s_}}%KrC?(fp9RG1#)!}
z8v_FaFUYYH3=9k$j4aGdj6#A;j7*Fo><AL9N|W&xXKrdqA~?5eaurE~auIW4QgRU}
zPK!WxM=>WAn?T&d36d2A7jSw=>7fYhB#@<$kOMmeOn_W-i^B%ue>;$A#h_A-g++jo
KhmnJkhZz7XWKkjj
literal 0
HcmV?d00001
diff --git a/input/get/__pycache__/nature.cpython-39.pyc b/input/get/__pycache__/nature.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8c6ae402187f9b6c4bda32d8c3b57e41947bfce6
GIT binary patch
literal 1757
zcmYe~<>g{vU|=}ZIW4i1oq^#oh=Yt-7#J8F7#J9e4Hy_0QW&BbQW#U1au{=&qL>&#
zY~~#1T$U&nMh16=6qXd$7KRkoRHkO;DAp9VU<OV0s%|dljLe)Ah2)&X;$nsTGzG8x
z(xSY?9Jkbx<c!oJuF&Gd^i(Sa=Zw_kY=z7;h0vlLh2+FMg``x4(&E$<h4Rdj3<dS%
z#Ju>@;?(%kq8xQD1qevYOHnAvNX=770~w`IP@0sJnVeXXnV$#Ml%84=k0h$j^%CSU
zO~zY%sBX|?yu}@W(47oYg^b}r;K9JakjfCnn8Fanl)@OroX!x%lFFLOmdc*OG>0jL
zIfbQ#rI|5`11!b~7Gq6e1B-E`vZk=7aI`QqGe&Wza0WAIa@}HwhC!7T*h|I9MTrHe
z#V8)hO)W`GNi0cJNGr<ERY+7QD9SI(Oi4{qC@snXYtm%8#avpHbBnDgwWPEtFPRa^
z;UG2$JA<MR<cSo<U<OU5Drc}xP#}Usy%-ei>6vAzc_332ax(L>ixo=p6%rMSOA89}
zi%L>c6tW<ZrU%#Qwvs`Uv51v{fuV>UM*K3+&&bbB)lbXPFG?-QFV@e@D=00|Ehx&*
zO3f~T@buGDOZ4*+OG=AU^$IF)aU(^n1jw08Aop`r2}6TM4@n-yZ=giW!N9-(_S-E6
z28I%b1&lQe3mIz}Qy6O)vzW4&Q<zeiGZ|A@dKnk6q_8ez6lbVqg3GWW%hWQ%#o1BB
zS>WOvDB`T?47F_O47KcFdDaxB6i$e|3q!0(Ek_O80=60sh^-4585s&Y;Oe-L)N$6Z
zFJP<TL{hh*guRBThPj5VhNXtJhCPM5nLU_6lc&lM9`4RXsfi`2#R`cENGVn~Gq1QL
zF)uk45kFM|86_nJ#a8<IDfyXt`9<maw^;HLb5o<3UHm;Y8E>&BmXs6~-(pYB&nrpI
zD~aMu&MX1vo%oW>lAP2iF*qL@^$_tY(SoAP;#@tXY~_+zl3K-;lB|~ua$0^7m|a|&
zl$DxXQUpqVnjA%-SiQvo%8$kQr3JTGGEx&$Zn30g=B3<XPERel#SUUR=H%RBODrfz
z%}Xg_W?*2@<N~L!TPz?wQ5^9p`I(^nAH@c7N)$&t)M-&%kZfL@k(v_48xQhQQD#zU
zNq$jr6lXltDaBFjPzT;(hYBH5ZV@Oc-Qov15Xomspacm@l?-fLOfrlTV93JA!X(Bh
z1jbe3uw;s+6Qc+Lg#$RLg0mq*FoPzeACmR(ECg`~Pf2QVNj$h%OD(bmxdIe`3`|ub
zF#C`d_-XRo;)st2#cq83Ew1?Z-29Z%oYeUETRidcg{6r(P#O04_>}zQ`1mNH;Lv~o
z|DX_8mv}G#&>%lYpWs_O#h~a<&P^@J$WOV&TwGFgizO*PKc|Qjl)FLEQ6vgtiGc`&
zbHOZ7;1z*9#s_k$00RR92NMe$3lkHg5GNC(kQ5UmSk_OItw@T2f#H@UxLnXnPc6}d
t#vshEkc1)#kw=ONaC!h6f*xofyKiyWK)h@Ra%V9c0|NsKI}aldGXVOz(6s;n
literal 0
HcmV?d00001
diff --git a/input/get/__pycache__/publication_interface.cpython-39.pyc b/input/get/__pycache__/publication_interface.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..cd087d9c0a0a26e010a6faa45f267a8bccf438f3
GIT binary patch
literal 2041
zcmYe~<>g{vU|_iZWpZK(7X!m%5C<7EGcYhXFfcF_2Qe@(q%cG=q%fv1<uK+lMKLjg
z*vvW1QOqffDa<)6Q7mAZHHtNbF@+_EEtfrt9jt~mha;CWij$GSogsxSg}sF#g}s?6
ziYtXVm_d`H%7M$JGA}VVGdZVHAv3oizo?{GAu%UMp|~J5IWsLYS-~s6v?wnz$1Sxa
zIU}{GSRpYlMIk4%xTIL2BqKFfkLxAKy_$@-SjrP~vi&p}Z*d2dCgo%%CzfR9=V>zD
zVu$KX2B|~FtT4Z2FfcHrGDI<^Fhnt>Fh((_vMgXtWn0LY#lC=JAwv{rIztp!Dt9VR
zDsL)p8j~bL3ez0M6y_9`7M5nlD85wgRL(TUR35M>YYJNnYcpdMe=2t>Z>m5F`y8ee
zjucL?O2HJaU<OU@TjK7iB}h*6%qvMPN=r;mt;*$6P*6|^&df{CNiE6GQz*$-NP&k<
z8p!|PkiixpMX4o4nW<%|3W*9xM(cX!6_+IDC8sK+<rgWWXO^YrDU=rF6oc*2WW2>z
zlv+|+l$Xqi6f7(Z3=E)<aR$Y@3j+f~IzugE2}22E4MQ_y3S$amIzt+BGgAtaBttDz
z4U-E)tXwT~3DW}R6y_S{g-j`orHn-iHH-^bYM2)?GBOk@)G!7!XtGr82U`mApmRoQ
za(1yoW|~4~o`QNoVo8R&LSj*>LKY;V<H0^nEmBC!%t?hrH^iCX2+u51$V<#kg&XFS
zSe%-oke{beo{?ArGcB`NA+toGJQI|RQWJ}kGZYdPQZm!hic<4R6jCyaQj<&aiz@Zt
zh6I-+=A|SSr6^>A?8q#}rpE6j69WT76=!s!ZdI(dUO}ZM>n)bN)QXZKkoYa8qSRZg
zxrrso8MoLH3kp*6QZ!j^v4A`m#Rv0IJlIE3TwogHi{e`>Afc5EMSKhl48QF4GxBp&
z_0zKSi&6{ni}f?}3Q9|K3ySiyQnO1SJpJ_468!>1`i{?pr5?S4%3FfzsU@hEiGgB~
z2Nb;=EQ}J29E<{tJd9PEI8vY<hJK8s0V*!QNduH=N*ER})-Wt&tYu6GB?d+phS-2w
z<|?HcrUgtT%nMjj7#FbCFsCr3Ft;*EGAv{SK}LpfhC(40h7z{Q1V#oBEMZS!K~>kx
z*u)sgP$*=;P$*Qx6wIK>S``3~EKj6DA}zl(FGayOKcy5ssenodh5R&Vk&>FCkPA@+
zH>QdQ9K0Ye>s8nKz5M(C|Nkl}x6GVW1@-D$b%o@_yb^_^RJZ|}97UjPQ6#{?z)-}^
zz`$^e6H;8|WG3C>g)rkGmfT`X%P-1JEV;$$T9KSu04j%WaYLN#T2z!@q{&hQijpW^
zXi5jChvHlOFm7^AVsUY5aS<=bDp1M*Cyye2kfl6GQB<r7id_j%?6Pt(vM_QmF)?y5
zvM_S}XZp{@%)=<hRHZ^hOc!f1-C`~+$|+)FU|>Lra8S7bssX?e4vKkLga<QdGWuyU
z6@dziTl^p=A*D%8#v(~fmlsJfFff>d91O}Y3`|w(_?(7hoS&x9EspqjP=1Mzzr_^~
z4dnRvTRidcg{6r(P#O04_>}zQ`1o7wpj-!v6_$X+k_?buP$r9yzr|LN2r2<?u@|Kl
z=jW8AMsb#8WERJRloyGE1Gl&&u_QA&H?<@qKjjt+C=K0WE-op8L^>#-i$K8v_6j6U
zP-6$2LO?>rLJSNH9E>b10*ow7OpFqIOpGFeOpIW8P3|H&kY!By#o(f&h!Yf8APq(G
zAaOxRx<m>Au%%JF5b^ZX61~LaVsOxd&BNx9TO2l!q-X~U>|&6USeSVjIlz#Ik%t8U
D-MT6t
literal 0
HcmV?d00001
diff --git a/input/get/acs.py b/input/get/acs.py
new file mode 100755
index 0000000..3a54a15
--- /dev/null
+++ b/input/get/acs.py
@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+
+"""
+Child class of JournalFetcher
+Usage: Check if Url can be used with 'can_use_url'
+ and then fetch publication with 'get_publication'
+"""
+
+import re
+
+from input.get.journal_fetcher import JournalFetcher
+from input.publication import Publication, Citation
+
+
+class Fetcher(JournalFetcher):
+ """
+ Specific Fetcher for the ACS journals.
+ """
+
+ # Constant for the abbreviations of the supported Journals
+ SUPPORTED_JOURNALS = ['1021']
+
+ @staticmethod
+ def can_use_url(url: str) -> bool:
+ """
+ Uses Regex to extract journal specific substrings in Doi.
+ TODO: Support non Doi-urls
+ """
+ matched_url = re.match(r'(https?://)?(doi.org/)?(10.(\d{4})/\w+.\S+)', url)
+ return matched_url[4] in Fetcher.SUPPORTED_JOURNALS
+
+ @staticmethod
+ def get_publication(url: str) -> Publication:
+ """
+ Fetches html and creates Beatifulsoup-instance in parent class.
+ Specific css-searches for ACS-Journals and creates Publication-instance.
+ """
+
+ # Creation of Soup
+ soup = JournalFetcher.get_soup(url)
+ soup_header = soup.select('.article_header')[0]
+ ref_cit_soup = soup
+
+ # Creates Publication
+ doi_url = soup_header.select('a[title="DOI URL"]')[0].string
+ title = soup_header.select(".hlFld-Title")[0].text
+
+ contributors = []
+ for author in soup_header.select(".hlFld-ContribAuthor"):
+ contributors.append(author.text)
+
+ journal = soup_header.select(".cit-title")[0].text
+
+ published = soup_header.select(".pub-date-value")[0].text
+
+ subjects = []
+ subject_soup = soup_header.select('.article_header-taxonomy')[0]
+ for subject in subject_soup.select('a'):
+ subjects.append(subject.text)
+
+ num_citations = 0
+
+
+ references = []
+ references_soup = ref_cit_soup.select('ol#references')
+ if references_soup != []:
+ for reference in references_soup[0].select('li'):
+ ref_doi = "https://doi.org/{}".format(reference.select('.refDoi')[0].text.strip()[5:])\
+ if reference.select('.refDoi') != [] else "None"
+ ref_title = reference.select('.NLM_article-title')[0].text\
+ if reference.select('.NLM_article-title') != [] else "None"
+ ref_journal = reference.select('i')[0].text\
+ if reference.select('i') != [] else "None"
+
+ ref_contributors=[]
+ for author in reference.select('.NLM_contrib-group'):
+ ref_contributors.append(author.text)
+
+ references.append(Citation(ref_doi, ref_title, ref_journal, ref_contributors, cit_type="Reference"))
+
+ citations = []
+ citation_soup = ref_cit_soup.select('.cited-content_cbyCitation')
+ if citation_soup != []:
+ for citation in citation_soup[0].select('li'):
+ cit_doi = citation.select('a[title="DOI URL"]')[0].text\
+ if citation.select('a[title="DOI URL"]') != [] else "None"
+ cit_title = citation.select('.cited-content_cbyCitation_article-title')[0].text\
+ if citation.select('.cited-content_cbyCitation_article-title')!= [] else "None"
+ cit_journal = citation.select('.cited-content_cbyCitation_journal-name')[0].text\
+ if citation.select('.cited-content_cbyCitation_journal-name') != [] else "None"
+ cit_contributors =[]
+ cit_contributors = citation.select('.cited-content_cbyCitation_article-contributors')[0].text.split(', ')
+ # clean up of the last Entry
+ cit_contributors_last = cit_contributors.pop().strip(". ")
+ if cit_contributors_last != '':
+ cit_contributors.append(cit_contributors_last)
+ citations.append(Citation(cit_doi, cit_title, cit_journal, cit_contributors, cit_type = "Citation"))
+
+ return Publication(doi_url, title, contributors, journal, published
+ , subjects, num_citations, references, citations)
+
+
+ @staticmethod
+ def test_fetcher():
+ pass
diff --git a/input/get/acs_fj.py b/input/get/acs_fj.py
new file mode 100755
index 0000000..2880838
--- /dev/null
+++ b/input/get/acs_fj.py
@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+
+"""
+Child class of JournalFetcher
+JCIM
+"""
+
+# import re
+from input.get.journal_fetcher import JournalFetcher
+from input.publication import Publication, Citation, Reference
+import requests as req
+from bs4 import BeautifulSoup as bs
+
+class Fetcher(JournalFetcher):
+
+ """
+ """
+
+ # TODO: Naming-Convention:
+ # Class: 'Fetcher'
+ # file: input_get_[journal-/organisation-name]
+ # format = "input_get_[a-z]*.py" allowed
+ # TODO: List of Compatable Journals
+ _SUPPORTED_JOURNALS = []
+
+ @staticmethod
+ def can_use_url(url: str) -> bool:
+ """
+ Checks if given url links to a supported journal.
+ """
+
+ # TODO: Check the URL for compatability
+ # re.match in _SUPPORTED_JOURNALS
+ return True
+
+ @staticmethod
+ def get_publication(url: str) -> Publication:
+ return input(url)
+
+
+ @staticmethod
+ def test_fetcher():
+ pass
+
+def get_article_info(soup):
+ header = soup.find('div', class_ = 'article_header-left pull-left')
+ article_title = header.find('span', class_ = 'hlFld-Title').text
+ publication_date = header.find('span', class_ = 'pub-date-value').text
+ for link in header.find('div', class_ = 'article_header-doiurl'):
+ doi_url = link.get('href')
+ subs = header.find('div', class_ = 'article_header-taxonomy')
+ subjects = []
+ for sub in subs.find_all('a'):
+ subjects.append(sub.get('title'))
+ cons = header.find('ul', class_ = 'loa')
+ contributors = []
+ for con in cons.find_all('span', class_ = 'hlFld-ContribAuthor'):
+ contributors.append(con.text)
+ numc = header.find('div', class_ = 'articleMetrics_count')
+ if not numc.a:
+ num_citations = 0
+ else:
+ num_citations = numc.a.text
+ pub = Publication(doi_url, article_title, contributors, "JCIM",
+ publication_date, subjects, num_citations)
+ #pub = Publication(article_title, publication_date, contributors, doi_url,
+ # subjects, num_citations)
+ return pub
+
+
+def get_citation_info(pub, num_citations, soup):
+ details = soup.find('ol', class_ = 'cited-content_cbyCitation')
+ titles = []
+ for title in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-title'):
+ titles.append(title.text.replace('.', ''))
+ journal_names = []
+ for name in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_journal-name'):
+ journal_names.append(name.text)
+ doi_urls = []
+ for url in details.find_all('a'):
+ doi_urls.append(url.get('href'))
+ # TODO: There are a few diffrent types how Contributors are listed
+ contributors = []
+ for contrib in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-contributors'):
+ contributors.append(contrib.text)
+ for i in range(0, int(num_citations)):
+ pub.citations.append(Citation(doi_urls[i], titles[i], journal_names[i], \
+ contributors[i]))
+
+def input(url):
+ html_text = req.get(url).text
+ soup = bs(html_text, 'html.parser')
+
+ pub = get_article_info(soup)
+ if int(pub.num_citations) > 0:
+ get_citation_info(pub, int(pub.num_citations), soup)
+ return pub
diff --git a/input/get/journal_fetcher.py b/input/get/journal_fetcher.py
new file mode 100755
index 0000000..097eb24
--- /dev/null
+++ b/input/get/journal_fetcher.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+
+"""
+Parent class for specific Journal
+"""
+
+from abc import ABCMeta, abstractmethod
+from bs4 import BeautifulSoup
+import requests
+from input.publication import Publication
+
+
+class JournalFetcher(metaclass=ABCMeta):
+ """
+ This is a abstract-class for fetcher modules
+ """
+ @staticmethod
+ def get_soup(url: str) -> BeautifulSoup:
+ """
+ Retrieves webside-html and returns a BeautifulSoup-instance
+
+ Parameters:
+ -----------
+ :type url: str
+ :param url: doi-url to a publication
+ :return: BeatifulSoup-instance
+ """
+ try:
+ req = requests.get(url)
+ except requests.exceptions.HTTPError as err:
+ raise SystemExit(err)
+
+ return BeautifulSoup(req.content, 'html.parser')
+
+ @staticmethod
+ @abstractmethod
+ def can_use_url(url: str) -> bool:
+ """
+ Abstract-function to be implemented in subclass.
+ Checks if given url links to a supported journal
+ """
+ raise AttributeError("JournalFetcher for '{}' hasnt implemented 'can_use_url()'".format(url))
+
+ @staticmethod
+ @abstractmethod
+ def get_publication(url: str) -> Publication:
+ """
+ Abstract-function to be implemented in subclass.
+ Creates a Publication-instance.
+ """
+ raise AttributeError("JournalFetcher for '{}' hasnt implemented 'get_publication()'".format(url))
+
+ @staticmethod
+ @abstractmethod
+ def test_fetcher():
+ """
+ Abstract-function to be implemented in subclass.
+ Unit-test for the class.
+ """
+ raise AttributeError("JournalFetcher: Subclass hasnt implemented 'test_fetcher()'")
diff --git a/input/get/nature.py b/input/get/nature.py
new file mode 100755
index 0000000..d08d74f
--- /dev/null
+++ b/input/get/nature.py
@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+
+"""
+Child class of JournalFetcher
+Usage: Check if Url can be used with 'can_use_url'
+ and then fetch publication with 'get_publication'
+"""
+
+# import re
+from input.get.journal_fetcher import JournalFetcher
+from input.publication import Publication
+
+
+class Fetcher(JournalFetcher):
+
+ """
+ scrapes publication metadata from a provided url
+ """
+
+ # TODO: List of Compatable Journals
+ # NOTE: nature does not use journal names in doi links, must match by 10.xxxx identifier instead
+ SUPPORTED_JOURNALS = []
+
+ @staticmethod
+ def can_use_url(url: str) -> bool:
+ """
+ Checks if given url links to a supported journal.
+ """
+
+ # TODO: Check the URL for compatability
+ # re.match in SUPPORTED_JOURNALS
+ return False
+
+ @staticmethod
+ def get_publication(url: str) -> Publication:
+ """
+ Creates a Publication-instance.
+ """
+
+ soup = JournalFetcher.get_soup(url)
+
+ _doi_url = "https://doi.org/" + soup.head.find(attrs={"name": "DOI"}).get("content")
+ _title = soup.head.find(attrs={"name": "citation_title"}).get("content")
+ _journal = soup.head.find(attrs={"name": "citation_journal_title"}).get("content")
+ _published = soup.head.find(attrs={"name": "prism.publicationDate"}).get("content")
+ _contributors = []
+ _subjects = []
+
+ for creator in soup.head.findAll(attrs={"name": "dc.creator"}):
+ _contributors.append(creator.get("content"))
+
+ for subject in soup.head.findAll(attrs={"name": "dc.subject"}):
+ _subjects.append(subject.get("content"))
+
+ return Publication(_doi_url, _title, _contributors, _journal, _published, _subjects, 0)
+
+ # TODO: Exceptions-handling
+ # raise ValueException("Cant Fetch: '{}'".format(error))
+ # return None
+
+ @staticmethod
+ def test_fetcher():
+ pass
diff --git a/input/get/template_.py b/input/get/template_.py
new file mode 100755
index 0000000..72f3cf9
--- /dev/null
+++ b/input/get/template_.py
@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+
+"""
+Child class of JournalFetcher
+Usage: None, this is just a template and should be ignored
+"""
+
+# import re
+from input.get.journal_fetcher import JournalFetcher
+from input.publication import Publication
+
+
+class Fetcher(JournalFetcher):
+
+ """
+ This is only a template and therefore has no functionality
+ """
+
+ # TODO: Naming-Convention:
+ # Class: 'Fetcher'
+ # file: [journal-/organisation-name]
+ # format = "[a-z]*.py" allowed
+ # TODO: List of Compatable Journals
+ SUPPORTED_JOURNALS = []
+
+ @staticmethod
+ def can_use_url(url: str) -> bool:
+ """
+ Checks if given url links to a supported journal.
+ """
+
+ # TODO: Check the URL for compatability
+ # url_re = re.match(r'(https?://)?(doi.org/)?(10.(\d{4})/\w+.\S+)', url)
+ # return url_re[4] in SUPPORTED_JOURNALS
+ return False
+
+ @staticmethod
+ def get_publication(url: str) -> Publication:
+ """
+ Creates a Publication-instance.
+ """
+
+ # TODO: Fetch data from the HTML
+ # soup = JournalFetcher.get_soup(url)
+ # doi,title,contributors[],journal,publication_date,subjects[],references[],citations[]
+ # TODO: Create new Publication-instance
+ # return Publication(doi,title,contributors[],journal,publication_date,subjects[],num_citation=None ,references[],citations[])
+ return None
+
+ @staticmethod
+ def test_fetcher():
+ pass
diff --git a/input/interface.py b/input/interface.py
new file mode 100755
index 0000000..c0d6df4
--- /dev/null
+++ b/input/interface.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+
+"""
+Interface for the Input-Package only this should be accessed from outside this Package.
+
+"""
+from os import walk
+import importlib
+import pathlib
+import re
+from input.publication import Publication
+
+class InputInterface:
+ """
+ Singleton which dynamically imports and manages fetchers
+ """
+
+ get_path = None
+ fetcher_classes=[]
+
+ @staticmethod
+ def get_publication(url: str) -> Publication:
+ """
+ The interface-method to get a Publication-instance
+
+ Parameters
+ ----------
+ :param url: url to a Publication
+ :type url: str
+ :return: Publication instance or None if not supported
+ """
+ # Initializes 'fetcher_classes', the list of imported modules
+ if InputInterface.fetcher_classes ==[]:
+ InputInterface.get_fetcher_classes()
+ if InputInterface.fetcher_classes ==[]:
+ raise AttributeError("No specific Fetchers where found at: '{}'"
+ .format(InputInterface.get_path))
+
+ # Checks if module supports the 'url' and returns a Publication if it does.
+ for fetcher_class in InputInterface.fetcher_classes:
+ if fetcher_class.can_use_url(url):
+ return fetcher_class.get_publication(url)
+
+ # No Module for given url was found
+ return None
+
+
+ @staticmethod
+ def get_fetcher_classes():
+ """
+ Searches in 'get', if there are [a-z]*.py modules (specific Fetchers)
+ and tries to import them.
+ Saves found modules in 'fetcher_files'.
+ """
+
+ # Path to 'get'-package
+ InputInterface.get_path = '{}/get'.format(pathlib.Path(__file__).parent.resolve())
+
+ # Searches for modules with given Pattern
+ fetcher_file_names=[]
+ for file in next(walk(InputInterface.get_path), (None, None, []))[2]:
+ if re.match(r'[a-z]+.py', file) is not None:
+ fetcher_file_names.append(file)
+
+ if fetcher_file_names !=[]:
+ print("Found following Modules: {}".format(", ".join(fetcher_file_names)))
+
+ # Tries to import those modules and saves their 'Fetcher'-class
+ for file in fetcher_file_names:
+ try:
+ fetcher_class = importlib.import_module("input.get.{}".format(file[:-3]))
+ try:
+ InputInterface.fetcher_classes.append(fetcher_class.__getattribute__('Fetcher'))
+ except Exception as error:
+ print("Module '{}' does not have a 'Fetcher'-class".format(file[:-3]))
+ except Exception:
+ raise ImportError("Module '{}' can not be imported".format(file[:-3]))
diff --git a/input/publication.py b/input/publication.py
new file mode 100755
index 0000000..792d779
--- /dev/null
+++ b/input/publication.py
@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+
+class Publication:
+ """
+ Represents a Publications
+ """
+ def __init__(self, doi_url: str, title: str
+ , contributors: str, journal: str
+ , publication_date: str, subjects: list[str], num_citations: int = None
+ , references: list[any] = None, citations: list[any] = None ):
+ """
+ Parameters
+ ----------
+ :param doi_url: doi_url of the publication
+ :type doi_url: str
+ :param title: title of the publication
+ :type title: str
+ :param contributors:list of all contributors
+ :type contributors: list[]
+ :param published: date of release
+ :type published: str
+ :param subjects: the subject of the Publication
+ :type subjects: list[str]
+ :param references: the Citation which is been referenced by this Publication
+ :type references: list[any]
+ :param citations: the Citation which references this Publication
+ :type citations: list[any]
+ :return: None
+ """
+ self.doi_url = doi_url
+ self.title = title
+ self.contributors = contributors
+ self.journal = journal
+ self.publication_date = publication_date
+ self.subjects = subjects
+ if references is None:
+ self.references = []
+ else:
+ self.references = references
+ if citations is None:
+ self.citations = []
+ else:
+ self.citations = citations
+ if num_citations is None:
+ self.num_citations = len(self.citations)
+ else:
+ self.num_citations = num_citations # braucht man nicht einfach len(citations)
+
+
+ def __str__(self) -> str:
+ return ("Title: {}\n"
+ "Doi-url: {}\n"
+ "Authors: {}\n"
+ "Journal: {}\n"
+ "Published on: {}\n"
+ "Subjects: {}\n"
+ "References: \n{}\n"
+ "Citations: \n{}\n")\
+ .format(self.title, self.doi_url, ", ".join(self.contributors)
+ , self.journal, self.publication_date
+ , ", ".join(self.subjects)
+ , "\n".join(self.get_citation_string(self.references))
+ , "\n".join(self.get_citation_string(self.citations)))
+
+ @staticmethod
+ def get_citation_string(citations):
+ if citations == []:
+ return ["None"]
+ else:
+ citation_string = []
+ for citation in citations:
+ citation_string.append(citation.__str__())
+ return citation_string
+
+ def citations(self, citation) -> None:
+ """
+ Appends a list of Citations or Citation to self.citations.
+
+ Parameter
+ ---------
+ :param citation: Citation or Reference of the Publication
+ :type citation: Citation or list[Citation]
+ :return: self.citations
+ """
+ if type(citation) is Citation:
+ self.citations.append(citation)
+
+ # Checks if 'citation' is a list of Citations
+ elif type(citation) is list:
+ for _cit in citation:
+ if type(_cit) is Citation:
+ self.citations.append(_cit)
+ else:
+ raise TypeError("_set_citation expects Citations or List of Citations, not: '{}'"
+ .format(type(_cit)))
+ else:
+ raise TypeError("_set_citation expects Citations or List of Citations, not: '{}'"
+ .format(type(citation)))
+
+ return self.citations
+
+ def __eq__(self, other) -> bool:
+ """ Compares the unique doi_url of two Publications"""
+ return self.doi_url == other.doi_url
+
+ def print_pub(self):
+ print(f'''Article title: {self.title}
+Publication date: {self.publication_date}
+DOI-URL: {self.doi_url}
+
+Subjects:''')
+ print(*(self.subjects), sep = ", ")
+ print('\nContributors:')
+ print(*(self.contributors), sep = ", ")
+
+ if int(self.num_citations) > 0:
+ if int(self.num_citations) == 1:
+ print(f'\nThis publication is cited by the following publication:\n')
+ else:
+ print(f'\nThis publication is cited by the following {self.num_citations} publications:\n')
+ for citation in self.citations:
+ print(f'''
+ Title: {citation.title}
+ Journal: {citation.journal}
+ Contributors: {citation.contributors}
+ DOI-URL: {citation.doi_url}
+ ''')
+ else:
+ print('\nThis publication is not cited by any other publication.')
+
+
+
+
+class Citation:
+ def __init__(self, doi_url: str, title: str
+ , journal: str, contributors: list[str]
+ , cit_type: str = "Citation"):
+ """
+ Parameters
+ ----------
+ :param doi_url: doi_url of the publication
+ :type doi_url: str
+ :param title: title of the publication
+ :type title: str
+ :param contributors: list of all contributors
+ :type contributors: list[str]
+ :param cit_type: Specifies if Reference or Citation
+ :type cit_type: str
+ :return: None
+ """
+
+ self.title = title
+ self.doi_url = doi_url
+ self.journal = journal
+ self.contributors = contributors
+ self.cit_type = cit_type
+
+ def __str__(self) -> str:
+ return ("\t{}-Title: {}\n"
+ "\t{}-Doi: {}\n"
+ "\t{}-Journal: {}\n"
+ "\t{}-Contributors: {}\n")\
+ .format(self.cit_type, self.title
+ , self.cit_type, self.doi_url
+ , self.cit_type, self.journal
+ , self.cit_type, ", ".join(self.contributors))
+
+
+# This is just a replica of Citations
+class Reference:
+ def __init__(self, doi_url: str, title: str, journal: str, contributors: list[str]):
+ self.title = title
+ self.doi_url = doi_url
+ self.journal = journal
+ self.contributors = contributors
+
+ def __str__(self) -> str:
+ return ("\tReferences-Title: {}\n"
+ "\tReferences-Doi: {}\n"
+ "\tReferences-Journal: {}\n"
+ "\tReferences-Contributors: {}")\
+ .format(self.title, self.doi_url
+ , self.journal, ", ".join(self.contributors))
diff --git a/input/requirements.txt b/input/requirements.txt
new file mode 100644
index 0000000..a151126
--- /dev/null
+++ b/input/requirements.txt
@@ -0,0 +1,2 @@
+beautifulsoup4
+requests
\ No newline at end of file
diff --git a/input/tempdir/input_fj.py b/input/tempdir/input_fj.py
new file mode 100755
index 0000000..00bb012
--- /dev/null
+++ b/input/tempdir/input_fj.py
@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Functions for information retrieval of articles from the ACS journal JCIM
+
+"""
+
+__author__ = "Florian Jochens"
+__email__ = "fj@andaco.de"
+__status__ = "Production"
+#__copyright__ = ""
+#__credits__ = ["", "", "", ""]
+#__license__ = ""
+#__version__ = ""
+#__maintainer__ = ""
+
+from bs4 import BeautifulSoup as bs
+import requests as req
+import sys
+from pathlib import Path
+
+class Publication:
+ #_registry = []
+ _citations = []
+
+ def __init__(self, title, publication_date, contributors, doi_url,
+ subjects, num_citations):
+ #self._registry.append(self)
+ self.title = title
+ self.publication_date = publication_date
+ self.contributors = contributors
+ self.doi_url = doi_url
+ self.subjects = subjects
+ self.num_citations = num_citations
+
+class Citation:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
+def get_article_info(soup):
+ header = soup.find('div', class_ = 'article_header-left pull-left')
+ article_title = header.find('span', class_ = 'hlFld-Title').text
+ publication_date = header.find('span', class_ = 'pub-date-value').text
+ for link in header.find('div', class_ = 'article_header-doiurl'):
+ doi_url = link.get('href')
+ subs = header.find('div', class_ = 'article_header-taxonomy')
+ subjects = []
+ for sub in subs.find_all('a'):
+ subjects.append(sub.get('title'))
+ cons = header.find('ul', class_ = 'loa')
+ contributors = []
+ for con in cons.find_all('span', class_ = 'hlFld-ContribAuthor'):
+ contributors.append(con.text)
+ numc = header.find('div', class_ = 'articleMetrics_count')
+ if not numc.a:
+ num_citations = 0
+ else:
+ num_citations = numc.a.text
+
+ pub = Publication(article_title, publication_date, contributors, doi_url,
+ subjects, num_citations)
+ return pub
+
+def get_download_url():
+ export = soup.find('div', class_ = 'cit-download-dropdown_content')
+ url = 'https://pubs.acs.org'
+ for link in export.find_all('a'):
+ if link.get('title') == 'Citation and references':
+ url += link.get('href')
+ print(url)
+ return url
+
+def download(url): # Download citation and references file
+ if url.find('='):
+ filename = url.rsplit('=', 1)[1]
+ path = Path(('./files/' + filename))
+ if path.is_file():
+ print("File already exists")
+ else:
+ print("File does not exist")
+
+def get_citation_info(pub, num_citations, soup):
+ pub._citations = []
+ details = soup.find('ol', class_ = 'cited-content_cbyCitation')
+ titles = []
+ for title in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-title'):
+ titles.append(title.text.replace('.', ''))
+ journal_names = []
+ for name in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_journal-name'):
+ journal_names.append(name.text)
+ doi_urls = []
+ for url in details.find_all('a'):
+ doi_urls.append(url.get('href'))
+ contributors = []
+ for contrib in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-contributors'):
+ contributors.append(contrib.text)
+ for i in range(0, int(num_citations)):
+ pub._citations.append(Citation(titles[i], journal_names[i],
+ contributors[i], doi_urls[i]))
+def print_pub_info(pub):
+ print(f'''Article title: {pub.title}
+Publication date: {pub.publication_date}
+DOI-URL: {pub.doi_url}
+
+Subjects:''')
+ print(*(pub.subjects), sep = ", ")
+ print('\nContributors:')
+ print(*(pub.contributors), sep = ", ")
+
+ if int(pub.num_citations) > 0:
+ if int(pub.num_citations) == 1:
+ print(f'\nThis publication is cited by the following publication:\n')
+ else:
+ print(f'\nThis publication is cited by the following {pub.num_citations} publications:\n')
+ for citation in pub._citations:
+ print(f'''
+ Title: {citation.title}
+ Journal: {citation.journal}
+ Contributors: {citation.contributors}
+ DOI-URL: {citation.doi_url}
+ ''')
+ else:
+ print('\nThis publication is not cited by any other publication.')
+
+def input(url):
+ html_text = req.get(url).text
+ soup = bs(html_text, 'html.parser')
+
+ pub = get_article_info(soup)
+ if int(pub.num_citations) > 0:
+ get_citation_info(pub, int(pub.num_citations), soup)
+ return pub
+
+#if len(sys.argv) != 2:
+# sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+# exit(1)
+#url = sys.argv[1]
+#pub = input(url)
+#print_pub_info(pub)
diff --git a/input/pub.py b/input/tempdir/pub.py
similarity index 100%
rename from input/pub.py
rename to input/tempdir/pub.py
diff --git a/input/tempdir/test.py b/input/tempdir/test.py
new file mode 100755
index 0000000..bdd12e8
--- /dev/null
+++ b/input/tempdir/test.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python3
+
+from input_fj import input, print_pub_info
+import sys
+
+if len(sys.argv) != 3:
+ sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+ exit(1)
+url = sys.argv[1]
+url2 = sys.argv[2]
+pub = input(url)
+print_pub_info(pub)
+pub2 = input(url2)
+print_pub_info(pub2)
+
diff --git a/input/test_doi.txt b/input/test_doi.txt
new file mode 100644
index 0000000..ced8c84
--- /dev/null
+++ b/input/test_doi.txt
@@ -0,0 +1,4 @@
+https://doi.org/10.1021/acs.jcim.1c00203
+https://doi.org/10.1021/acs.jcim.1c00917
+https://doi.org/10.1021/acs.jmedchem.0c01332
+10.1093/bioinformatics/btaa190
diff --git a/input/test_input_get_publication.py b/input/test_input_get_publication.py
new file mode 100755
index 0000000..941dbc7
--- /dev/null
+++ b/input/test_input_get_publication.py
@@ -0,0 +1,28 @@
+import unittest
+"""
+Testing the Publication fetcher
+
+Publication 1: 'https://doi.org/10.1021/acs.jcim.1c00203'
+Publication 2: 'doi.org/10.1021/acs.jcim.1c00917'
+Publication 3: '10.1038/nchem.1781'
+Publication 4: '11.12/jaj'
+Publication 5: '11.12/'
+Publication 6: 'https://doi.org/10.1021/acs.jmedchem.0c01332' # Paper is a PDF
+"""
+
+
+class TestGetPublication(unittest.TestCase):
+
+ def test_publication1(self):
+ pass
+
+ def test_publication2(self):
+ pass
+
+ def test_publication3(self):
+ pass
+
+
+if __name__=="__main__":
+ print("test")
+ unittest.main()
\ No newline at end of file
diff --git a/input_old/README.md b/input_old/README.md
new file mode 100644
index 0000000..76bd11d
--- /dev/null
+++ b/input_old/README.md
@@ -0,0 +1,3 @@
+# Projekt CiS-Projekt 2021/22
+Input-Skripts
+
diff --git a/input/__pycache__/input_fj.cpython-39.pyc b/input_old/__pycache__/input_fj.cpython-39.pyc
similarity index 100%
rename from input/__pycache__/input_fj.cpython-39.pyc
rename to input_old/__pycache__/input_fj.cpython-39.pyc
diff --git a/input/example_urls b/input_old/example_urls
similarity index 100%
rename from input/example_urls
rename to input_old/example_urls
diff --git a/input_old/input_fj.py b/input_old/input_fj.py
new file mode 100755
index 0000000..ecc8e68
--- /dev/null
+++ b/input_old/input_fj.py
@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+"""
+Functions for information retrieval of articles from the ACS journal JCIM
+
+"""
+
+__author__ = "Florian Jochens"
+__email__ = "fj@andaco.de"
+__status__ = "Production"
+#__copyright__ = ""
+#__credits__ = ["", "", "", ""]
+#__license__ = ""
+#__version__ = ""
+#__maintainer__ = ""
+
+from bs4 import BeautifulSoup as bs
+import requests as req
+import sys
+from pathlib import Path
+
+class Publication:
+ #_registry = []
+ _citations = []
+ _references = []
+
+ def __init__(self, title, publication_date, contributors, doi_url,
+ subjects = None, num_citations = None):
+ #self._registry.append(self)
+ self.title = title
+ self.publication_date = publication_date
+ self.contributors = contributors
+ self.doi_url = doi_url
+ self.subjects = subjects
+ self.num_citations = num_citations
+ #self._citations = []
+ #self._references = []
+
+class Citation:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
+class References:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
+def get_article_info(soup):
+ header = soup.find('div', class_ = 'article_header-left pull-left')
+ article_title = header.find('span', class_ = 'hlFld-Title').text
+ publication_date = header.find('span', class_ = 'pub-date-value').text
+ for link in header.find('div', class_ = 'article_header-doiurl'):
+ doi_url = link.get('href')
+ subs = header.find('div', class_ = 'article_header-taxonomy')
+ subjects = []
+ for sub in subs.find_all('a'):
+ subjects.append(sub.get('title'))
+ cons = header.find('ul', class_ = 'loa')
+ contributors = []
+ for con in cons.find_all('span', class_ = 'hlFld-ContribAuthor'):
+ contributors.append(con.text)
+ numc = header.find('div', class_ = 'articleMetrics_count')
+ if not numc.a:
+ num_citations = 0
+ else:
+ num_citations = numc.a.text
+
+ pub = Publication(article_title, publication_date, contributors, doi_url,
+ subjects, num_citations)
+ return pub
+
+def get_download_url():
+ export = soup.find('div', class_ = 'cit-download-dropdown_content')
+ url = 'https://pubs.acs.org'
+ for link in export.find_all('a'):
+ if link.get('title') == 'Citation and references':
+ url += link.get('href')
+ print(url)
+ return url
+
+def download(url): # Download citation and references file
+ if url.find('='):
+ filename = url.rsplit('=', 1)[1]
+ path = Path(('./files/' + filename))
+ if path.is_file():
+ print("File already exists")
+ else:
+ print("File does not exist")
+
+def get_citation_info(pub, num_citations, soup):
+ pub._citations = []
+ details = soup.find('ol', class_ = 'cited-content_cbyCitation')
+ titles = []
+ for title in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-title'):
+ titles.append(title.text.replace('.', ''))
+ journal_names = []
+ for name in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_journal-name'):
+ journal_names.append(name.text)
+ doi_urls = []
+ for url in details.find_all('a'):
+ doi_urls.append(url.get('href'))
+ contributors = []
+ for contrib in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-contributors'):
+ contributors.append(contrib.text)
+ for i in range(0, int(num_citations)):
+ pub._citations.append(Citation(titles[i], journal_names[i],
+ contributors[i], doi_urls[i]))
+def print_pub_info(pub):
+ print(f'''Article title: {pub.title}
+Publication date: {pub.publication_date}
+DOI-URL: {pub.doi_url}
+
+Subjects:''')
+ print(*(pub.subjects), sep = ", ")
+ print('\nContributors:')
+ print(*(pub.contributors), sep = ", ")
+
+ if int(pub.num_citations) > 0:
+ if int(pub.num_citations) == 1:
+ print(f'\nThis publication is cited by the following publication:\n')
+ else:
+ print(f'\nThis publication is cited by the following {pub.num_citations} publications:\n')
+ for citation in pub._citations:
+ print(f'''
+ Title: {citation.title}
+ Journal: {citation.journal}
+ Contributors: {citation.contributors}
+ DOI-URL: {citation.doi_url}
+ ''')
+ else:
+ print('\nThis publication is not cited by any other publication.')
+
+def input(url):
+ html_text = req.get(url).text
+ soup = bs(html_text, 'html.parser')
+
+ pub = get_article_info(soup)
+ if int(pub.num_citations) > 0:
+ get_citation_info(pub, int(pub.num_citations), soup)
+ return pub
+
+#if len(sys.argv) != 2:
+# sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+# exit(1)
+#url = sys.argv[1]
+#pub = input(url)
+#print_pub_info(pub)
diff --git a/input_old/pub.py b/input_old/pub.py
new file mode 100644
index 0000000..13b90e8
--- /dev/null
+++ b/input_old/pub.py
@@ -0,0 +1,32 @@
+class Publication:
+ #_registry = []
+ #_citations = []
+ #_references = []
+
+ def __init__(self, title, publication_date, contributors, doi_url,
+ subjects, num_citations):
+ #self._registry.append(self)
+ self.title = title
+ self.publication_date = publication_date
+ self.contributors = contributors
+ self.doi_url = doi_url
+ self.subjects = subjects
+ self.num_citations = num_citations
+ self.num_references = num_references
+ self._citations = []
+ self._references = []
+
+class Citation:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
+class References:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
diff --git a/input/test.py b/input_old/test.py
similarity index 100%
rename from input/test.py
rename to input_old/test.py
diff --git a/input/x b/input_old/x
similarity index 100%
rename from input/x
rename to input_old/x
--
GitLab