impact-factor 1.1.3__py3-none-any.whl

impact_factor/__init__.py

@@ -0,0 +1,12 @@
+import json
+from pathlib import Path
+
+
+BASE_DIR = Path(__file__).resolve().parent
+
+DEFAULT_DB = BASE_DIR.joinpath('data', 'impact_factor.sqlite3')
+DEFAULT_EXCEL = BASE_DIR.joinpath('data', '2022_JCR_IF.xlsx')
+
+version_info = json.load(BASE_DIR.joinpath('version.json').open())
+
+__version__ = version_info['version']

impact_factor/bin/_build.py

@@ -0,0 +1,80 @@
+import os
+
+import click
+
+from impact_factor import util, DEFAULT_EXCEL
+from impact_factor.core import NlmCatalog
+
+
+EPILOG = click.style('''
+\n\b
+examples:
+    impact_factor build -i tests/IF.xlsx
+\b
+    # with a ncbi api_key
+    impact_factor build -k YOUR_NCBI_API_KEY
+\b
+    # use a new dbfile [*recommend*]
+    impact_factor -d test.db build -i tests/IF.xlsx
+\b
+    # without nlm_catalog
+    impact_factor -d test.db build -i tests/IF.xlsx -n
+''', fg='yellow', italic=True)
+
+
+@click.command(
+    name='build',
+    help=click.style('build/update the database', italic=True, fg='green'),
+    no_args_is_help=True,
+    epilog=EPILOG,
+)
+@click.option('-i', '--excel', help='the excel file with IF')
+@click.option('-u', '--update', help='update all records', is_flag=True)
+@click.option('-f', '--force', help='force update when database already exists', is_flag=True)
+@click.option('-k', '--ncbi_api_key', help='specify a NCBI_API_KEY', envvar='NCBI_API_KEY', show_envvar=True)
+@click.option('-n', '--no-nlm', help='do not use nlm catalog', is_flag=True)
+@click.pass_context
+def main(ctx, **kwargs):
+
+    with ctx.obj['manager'] as manager:
+        if (key := kwargs['ncbi_api_key']):
+            NlmCatalog._api_key = key
+
+        if manager.query().count() > 0 and not kwargs['force']:
+            dbfile = ctx.obj['dbfile']
+            overwrite = click.confirm(f'db already exists, overwrite? [{dbfile}]')
+            if not overwrite:
+                exit()
+
+        for n, context in enumerate(util.parse_excel(kwargs['excel'])):
+            click.secho(f'>>> dealing with: [{n}]')
+            issn = context['issn']
+            eissn = context['eissn']
+            journal = context['journal']
+
+            record = manager.query('journal', journal).first()
+
+            # update when record is not in database, or force update
+            if record is None or kwargs['update']:
+
+                if not kwargs['no_nlm']:
+                    res = None
+                    if eissn:
+                        res = NlmCatalog.search(f'{eissn}[ISSN]')
+                    if not res and issn:
+                        res = NlmCatalog.search(f'{issn}[ISSN]')
+                    if not res:
+                        res = NlmCatalog.search(journal)
+
+                    if res:
+                        context.update(res)
+                    else:
+                        manager.logger.warning(f'no result for: {context}')
+
+                try:
+                    float(context['factor'])
+                except ValueError:
+                    continue
+
+                manager.insert(context, key='journal')
+

impact_factor/bin/_filter.py

@@ -0,0 +1,41 @@
+import json
+
+import click
+
+from impact_factor import util
+from impact_factor.core import Factor
+
+
+EPILOG = click.style('''
+\n\b
+examples:
+    impact_factor filter -m 50
+    impact_factor filter -m 50 -M 100
+    impact_factor filter -m 50 -M 100 -C
+    impact_factor filter -m 50 -M 100 -P
+''', fg='yellow', italic=True)
+
+@click.command(
+    name='filter',
+    help=click.style('filter according to factor', italic=True, fg='cyan'),
+    no_args_is_help=True,
+    epilog=EPILOG,
+)
+@click.option('-m', '--min-value', help='the min factor', type=float)
+@click.option('-M', '--max-value', help='the max factor', type=float)
+@click.option('-C', '--color', help='colorful output', is_flag=True)
+@click.option('-P', '--pubmed-filter', help='output pubmed filter format', is_flag=True)
+@click.option('-L', '--limit', help='the limit of results', type=int, default=100, show_default=True)
+@click.pass_context
+def main(ctx, **kwargs):
+
+    fa = Factor(ctx.obj['dbfile'])
+
+    res = fa.filter(**kwargs)
+
+    if kwargs['pubmed_filter']:
+        print(res)
+    else:
+        if kwargs['color']:
+            res = util.highlight_json(json.dumps(res, indent=2))
+        print(res)

impact_factor/bin/_search.py

@@ -0,0 +1,39 @@
+import json
+
+import click
+
+from impact_factor import util
+from impact_factor.core import Factor
+
+
+EPILOG = click.style('''
+\n\b
+examples:
+    impact_factor search nature         # search journal
+    impact_factor search 'nature c%'    # like search journal
+    impact_factor search 0028-0836      # search ISSN
+    impact_factor search 1476-4687      # search eISSN
+    impact_factor search 0410462        # search nlm_id
+    impact_factor search nature --color # colorful output
+''', fg='yellow', italic=True)
+
+@click.command(
+    name='search',
+    help=click.style('search record from database', italic=True, fg='magenta'),
+    no_args_is_help=True,
+    epilog=EPILOG,
+)
+@click.argument('value')
+@click.option('-f', '--field', help='specify a field to search')
+@click.option('-C', '--color', help='colorful output', is_flag=True)
+@click.pass_context
+def main(ctx, **kwargs):
+
+    fa = Factor(ctx.obj['dbfile'])
+
+    res = fa.search(kwargs['value'], key=kwargs['field'])
+
+    if kwargs['color']:
+        res = util.highlight_json(json.dumps(res, indent=2))
+
+    print(res)

impact_factor/bin/cli.py

@@ -0,0 +1,40 @@
+import os
+import click
+
+from impact_factor import version_info, DEFAULT_DB
+from impact_factor.core import FactorManager
+from impact_factor.bin._build import main as build_cli
+from impact_factor.bin._search import main as search_cli
+from impact_factor.bin._filter import main as filter_cli
+
+
+EPILOG = 'contact: {author} <{author_email}>'.format(**version_info)
+
+CONTEXT_SETTINGS = dict(help_option_names=['-?', '-h', '--help'])
+
+
+@click.group(
+    name=version_info['prog'],
+    help=click.style(version_info['desc'], italic=True, fg='cyan', bold=True),
+    context_settings=CONTEXT_SETTINGS,
+    no_args_is_help=True,
+    epilog=click.style(EPILOG, fg='bright_white', italic=True),
+)
+@click.option('-d', '--dbfile', help='the database file path', default=DEFAULT_DB, show_default=True)
+@click.version_option(version=version_info['version'], prog_name=version_info['prog'])
+@click.pass_context
+def cli(ctx, **kwargs):
+    ctx.ensure_object(dict)
+    ctx.obj['dbfile'] = kwargs['dbfile']
+    ctx.obj['manager'] = FactorManager(kwargs['dbfile'])
+
+
+def main():
+    cli.add_command(build_cli)
+    cli.add_command(search_cli)
+    cli.add_command(filter_cli)
+    cli()
+
+
+if __name__ == '__main__':
+    main()

impact_factor/core/__init__.py

@@ -0,0 +1,3 @@
+from .database import FactorData, FactorManager
+from .nlmcatalog import NlmCatalog
+from .factor import Factor

impact_factor/core/database.py

@@ -0,0 +1,20 @@
+import functools
+
+from sql_manager import DynamicModel, Manager
+from sqlalchemy import Column, Float, String
+
+
+columns = {
+    'nlm_id': Column(String, comment='the unique ID of NLM', default='.'),
+    'factor': Column(Float(3), comment='the IF of journal'),
+    'jcr': Column(String, comment='the partition of JCR', default='.'),
+    'journal': Column(String, comment='the title of journal', primary_key=True),
+    'journal_abbr': Column(String, comment='the abbreviation of journal', default='.'),
+    'issn': Column(String, comment='the ISSN of journal', default='.'),
+    'eissn': Column(String, comment='the eISSN of journal', default='.'),
+    'zky': Column(String, comment='the partition of ZKY', default='.'),
+}
+
+FactorData = DynamicModel('Factor', columns, 'factor')
+
+FactorManager = functools.partial(Manager, FactorData)

impact_factor/core/factor.py

@@ -0,0 +1,66 @@
+from sqlalchemy import func
+
+
+from impact_factor import DEFAULT_DB, util
+from .database import FactorData, FactorManager
+
+
+class Factor(object):
+    """Impact Factor ToolKits
+
+    examples:
+        >>> from impact_factor.core import Factor
+        >>> fa = Factor()
+        >>> fa.search('nature')
+        >>> fa.search('nature c%')
+        >>> fa.search('1579-3680', key='eissn')
+        >>> fa.filter(min_value=5, max_value=6)
+    """
+
+    def __init__(self, dbfile=DEFAULT_DB):
+        self.dbfile = dbfile
+        self.manager = FactorManager(dbfile)
+        self.query = self.manager.session.query(FactorData)
+
+    def search(self, value, key=None):
+        """
+            search something
+        """
+        default_keys = ['issn', 'eissn', 'nlm_id', 'journal', 'journal_abbr']
+        keys = [key] if key else default_keys
+
+        for field in keys:
+            if '%' in value:
+                result = self.query.filter(
+                    FactorData.__dict__[field].like(value))
+            else:
+                result = self.query.filter(
+                    func.lower(FactorData.__dict__[field]) == func.lower(value))
+
+            if result.count():
+                data = [util.record_to_dict(record) for record in result]
+                return data
+
+        return []
+
+    def filter(self, min_value=None, max_value=None, pubmed_filter=False, limit=None, **kwargs):
+        """
+            filter factor, or generate pubmed filter
+        """
+        query = self.query
+
+        if min_value is not None:
+            query = query.filter(FactorData.factor >= min_value)
+
+        if max_value is not None:
+            query = query.filter(FactorData.factor <= max_value)
+
+        if pubmed_filter:
+            query = query.filter(FactorData.nlm_id != '.', FactorData.factor != 0)
+            return util.pubmed_filter_builder(query)
+        
+        if limit and (count := query.count()) > limit:
+            self.manager.logger.warning(f'{count} records found, but limit is {limit}')
+            query = query.limit(limit)
+    
+        return [util.record_to_dict(record) for record in query]

impact_factor/core/nlmcatalog.py

@@ -0,0 +1,83 @@
+import os
+import time
+
+from webrequests import WebRequest as WR
+
+try:
+    import lxml.etree as ET
+except ImportError:
+    import xml.etree.cElementTree as ET
+
+
+class NlmCatalog(object):
+
+    base_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/'
+
+    _common_params = {'db': 'nlmcatalog'}
+
+    _api_key = os.getenv('NCBI_API_KEY')
+    if _api_key:
+        print(f'use api_key: {_api_key}')
+        _common_params['api_key'] = _api_key
+
+    @classmethod
+    def search(cls, term):
+        """
+            search term with efetch api,
+            and return nlm_id and journal_abbr
+        """
+        url = f'{cls.base_url}esearch.fcgi'
+        payload = {
+            **cls._common_params,
+            'term': term,
+            'format': 'json',
+        }
+
+        while True:
+            try:
+                result = WR.get_response(url, params=payload).json()['esearchresult']
+
+                if (count := result['count']) != '1':
+                    print(f'{term} has {count} result!')
+                    return False
+
+                nlm_id = result['idlist'][0]
+                xml = cls.fetch(nlm_id)
+                tree = cls.parse(xml)
+
+                context = {}
+                context['nlm_id'] = nlm_id
+                context['journal_abbr'] = tree.findtext('NLMCatalogRecord/MedlineTA')
+                
+                return context
+            except Exception as e:
+                print(e)
+                time.sleep(5)
+
+    @classmethod
+    def fetch(cls, id):
+        """
+            fetch xml string from nlm_id
+        """
+        url = f'{cls.base_url}efetch.fcgi'
+        payload = {
+            **cls._common_params,
+            'id': id,
+            'format': 'xml',
+        }
+        resp = WR.get_response(url, params=payload)
+
+        return resp.text
+
+    @classmethod
+    def parse(cls, xml):
+        """
+            return an etree object from xml
+        """
+        tree = ET.fromstring(xml)
+        return tree
+
+
+if __name__ == '__main__':
+    NlmCatalog.search('0334-9152[ISSN]')
+    NlmCatalog.fetch('101474857')

impact_factor/util/__init__.py

@@ -0,0 +1,38 @@
+from sqlalchemy.orm.state import InstanceState
+from pygments import highlight, lexers, formatters
+
+from .excel_parser import parse_excel
+
+
+def highlight_json(jsons):
+    """
+        highlight json string with pygments
+    """
+    return highlight(
+        jsons,
+        lexers.JsonLexer(),
+        formatters.TerminalFormatter()
+    )
+
+
+def record_to_dict(records):
+    """
+        convert Query result to dict
+    """
+    return {
+        k: v
+        for k, v in records.__dict__.items()
+        if not isinstance(v, InstanceState)
+    }
+
+
+def pubmed_filter_builder(query):
+    res = '|'.join(
+        record.issn
+        for record in query
+    )
+    if (length := len(res)) > 4000:
+        raise Exception(
+            f'pubmed filter limit 4000 characters, yours is {length}, please change your factor range'
+        )
+    return res

impact_factor/util/excel_parser.py

@@ -0,0 +1,44 @@
+import re
+import openpyxl
+
+
+def get_jcr(category):
+    """
+        get catagory of JCR
+    """
+    res = re.findall(r'[|(](Q\d)[)|]', category)
+    return res[0] if res else ''
+
+
+def parse_excel(infile):
+    """
+        parse excel file of JCR IF
+
+        fields: JIF, ISSN, EISSN, JCR, ZKY, JOURNAL, JOURNAL_ABBR
+    """
+    wb = openpyxl.load_workbook(infile)
+    ws = wb.active
+
+    for values in ws.values:
+        if values[0] is None:
+            continue
+        if values[0] in ('JOURNAL', 'Journal Name', 'Name'):
+            title = [v.upper() for v in values]
+            continue
+        context = dict(zip(title, values))
+        data = {}
+        data['factor'] = context['JIF']
+        data['issn'] = context['ISSN']
+        data['eissn'] = context['EISSN']
+        data['journal'] = context['JOURNAL']
+        data['jcr'] = context.get('JCR')
+        data['zky'] = context.get('ZKY')
+        data['journal_abbr'] = context.get('JOURNAL_ABBR')
+
+        yield data
+
+
+if __name__ == '__main__':
+    # for context in parse_excel('tests/2022_JCR_IF.xlsx'):
+    for context in parse_excel('tests/CopyofImpactFactor2024.xlsx'):
+        print(context)

impact_factor/version.json

@@ -0,0 +1,8 @@
+{
+    "prog": "impact_factor",
+    "desc": "Impact Factor Toolkits",
+    "url": "https://github.com/suqingdong/impact_factor",
+    "author": "suqingdong",
+    "author_email": "suqingdong1114@gmail.com",
+    "version": "1.1.3"
+}

impact_factor-1.1.3.dist-info/METADATA

@@ -0,0 +1,112 @@
+Metadata-Version: 2.1
+Name: impact_factor
+Version: 1.1.3
+Summary: Impact Factor Toolkits
+Home-page: https://github.com/suqingdong/impact_factor
+Author: suqingdong
+Author-email: suqingdong1114@gmail.com
+License: MIT License
+Project-URL: Documentation, https://impact_factor.readthedocs.io
+Project-URL: Tracker, https://github.com/suqingdong/impact_factor/issues
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Software Development :: Libraries
+Description-Content-Type: text/markdown
+Requires-Dist: lxml
+Requires-Dist: click
+Requires-Dist: openpyxl
+Requires-Dist: pygments
+Requires-Dist: webrequests
+Requires-Dist: sql_manager
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7539859.svg)](https://doi.org/10.5281/zenodo.7539859)
+
+[![Downloads](https://pepy.tech/badge/impact-factor)](https://pepy.tech/project/impact-factor)
+![PyPI - License](https://img.shields.io/pypi/l/mi?style=plastic)
+![PyPI](https://img.shields.io/pypi/v/impact_factor)
+![PyPI - Status](https://img.shields.io/pypi/status/impact_factor)
+
+
+# ***最新SCI期刊影响因子查询系统***
+- *已更新 **2025年数据***
+- *包含JCR分区表数据*
+- *包含中科院分区表数据*
+
+## Installation
+```bash
+python3 -m pip install -U impact_factor
+```
+
+## Use in CMD
+```bash
+impact_factor -h
+```
+![](https://suqingdong.github.io/impact_factor/src/help.png)
+
+### `build`
+> build/update the database
+
+```bash
+# optional, only required when you need build or update the database
+impact_factor build -i tests/IF.xlsx
+
+# with a ncbi api_key
+impact_factor build -k YOUR_NCBI_API_KEY
+
+# use a new dbfile [*recommend*]
+impact_factor -d test.db build -i tests/IF.xlsx
+
+# without nlm_catalog
+impact_factor -d test.db build -i tests/IF.xlsx -n
+```
+
+### `search`
+> search with `journal`, `journal_abbr`, `issn`, `eissn` or `nlm_id`
+
+```bash
+impact_factor search nature         # search journal
+impact_factor search 'nature c%'    # like search journal
+impact_factor search 0028-0836      # search ISSN
+impact_factor search 1476-4687      # search eISSN
+impact_factor search 0410462        # search nlm_id
+impact_factor search nature --color # colorful output
+```
+
+![](https://suqingdong.github.io/impact_factor/src/search.png)
+
+### `filter`
+> filter `factor` with `min_value` and `max_value`
+
+```bash
+impact_factor filter -m 100 -M 200 --color
+
+# output with pubmed filter format
+impact_factor filter -m 100 -M 200 --pubmed-filter
+```
+
+![](https://suqingdong.github.io/impact_factor/src/filter.png)
+
+## Use in Python
+```python
+from impact_factor.core import Factor
+
+fa = Factor()
+
+print(fa.dbfile)
+
+fa.search('nature')
+fa.search('nature c%')
+
+fa.filter(min_value=100, max_value=200)
+fa.filter(min_value=100, max_value=200, pubmed_filter=True)
+```
+
+## Documents
+https://impact-factor.readthedocs.io

impact_factor-1.1.3.dist-info/RECORD

@@ -0,0 +1,21 @@
+impact_factor/__init__.py,sha256=GoLmOoeOBxxraNS_coru5YOxnOdoWd7ZaEUIwttRfic,328
+impact_factor/version.json,sha256=oaNNCLe4twvsW4IYUQMXM4geY_Cdlc7aM9I9dy5p9xc,236
+impact_factor/bin/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+impact_factor/bin/_build.py,sha256=--HPgTvMD2oGbEfOF7U2-boJjMZtyT3BvSZVqIxQCJc,2691
+impact_factor/bin/_filter.py,sha256=JOnQSCTgKWM2IJK-sfF3ywWA5rq2rPkh-md6C1z5-Co,1206
+impact_factor/bin/_search.py,sha256=5YdUpt5-Y37IibfYHi16ZZXLWvVZ2MfZbOkWgk7sKzE,1112
+impact_factor/bin/cli.py,sha256=Fepdk5aPUcZ23OeKCTG9WCmzZWrEtfk_5881NM0Dzjg,1242
+impact_factor/core/__init__.py,sha256=tEhsbpbHE6KRnwXg5OMJNV-2dl1kQpRw0c3BPb8yrJY,113
+impact_factor/core/database.py,sha256=HARdbwyyzoxZXuq47pFc7xQadJiEwVxQFsRQccv_naY,852
+impact_factor/core/factor.py,sha256=GoFqPbmCuFVbo4s47zMAZhzSyGc9GXTD3ujVFacrNoo,2181
+impact_factor/core/nlmcatalog.py,sha256=OJpI-eh9D3zfqljqRSi611ka46dAAte6P-qt9lkYgrM,2144
+impact_factor/data/2022_JCR_IF.xlsx,sha256=NJoAKC7RL3W_oBvv72j9mU5bZydEEAPDO8sza-R6JKE,929300
+impact_factor/data/CopyofImpactFactor2024.xlsx,sha256=2POoCl1Nf7WCG242KUjvU06J43RIoCpT4BEucCxIQBw,1756410
+impact_factor/data/impact_factor.sqlite3,sha256=gZsaOr-BrnbJu95IEDkeDgwfnX3Vk6_w3Az_bNlFuyI,2813952
+impact_factor/util/__init__.py,sha256=oeF6lUgRWjm_yAAUqCAmy6SW22ojyjX_-ck_CiPI_xU,878
+impact_factor/util/excel_parser.py,sha256=v3fVAuhJh8tCrKhSvcEnBdhIkpNkHg3spKPvGHcfkAg,1204
+impact_factor-1.1.3.dist-info/METADATA,sha256=ncoZYPZkY5bx2F_uUctMR7JyxqnimoO8T-C5YoQM5uE,3182
+impact_factor-1.1.3.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+impact_factor-1.1.3.dist-info/entry_points.txt,sha256=9rttypvqMbdsY8U-EcXn0O8wwQeOV1f-t0J_sx5o9EY,93
+impact_factor-1.1.3.dist-info/top_level.txt,sha256=U32tP-Jpxs_YFYbWcRKpFd571Y9-XW9qKq61_ki69pY,14
+impact_factor-1.1.3.dist-info/RECORD,,

impact_factor-1.1.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.6.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

impact_factor-1.1.3.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+IF = impact_factor.bin.cli:main
+impact_factor = impact_factor.bin.cli:main

impact_factor-1.1.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+impact_factor