def __to_bibDict(self, P=1):
"""
私有方法
方法:对已按@分割后的 bib 文本内容进行解析 \n
返回值:bibItem字典\n
参数:P=1(表示简体转繁体)P=0(表示不转换)
"""
bibitemStr = self.bibitemStr
# 简体转繁体
if P == 1:
bibitemStr = cv.s2t(bibitemStr)
for i in self.__bibDict.keys():
y = re.findall(i + ".*?{(.*?)}", bibitemStr, re.I)
self.__bibDict[i] = ("" if y == [] else y[0])
# 提取 bibitem中的 引用标签字符串
x = bibitemStr.split(",")[0].split("{")
self.__bibDict["bibType"] = x[0].strip().lower()
self.__bibDict["citelabel"] = x[1].strip()
# re 判断是否包含中文
zhmodel = re.compile(u'[\u4e00-\u9fa5]')
if self.__bibDict["author"] != "":
match = zhmodel.search(self.__bibDict["author"])
self.__bibDict["lang"] = ('chinese' if match else "")
else:
match = zhmodel.search(self.__bibDict["title"])
self.__bibDict["lang"] = ('chinese' if match else "")
def core_lans(str, lans):
try:
assert lans in ['auto', 'cn', 'tc']
if lans in ['cn', 'tc']:
import inlp.convert.chinese as cv
return cv.t2s(str) if lans == 'cn' else cv.s2t(str)
else:
return str
except Exception as e:
logger.warning(e)
return str
def get_novel_name():
#請求當前章節頁面 params為請求引數
r = requests.get(req_url, params=req_header)
#soup轉換
soup = BeautifulSoup(r.text, "html.parser")
#以selcetor獲取章節名稱
novel_name = soup.select('#info h1')[0]
#刪去不必要的東西
pattern = re.compile(r'<(/*)h1>') #移除<h1> & </h1>
novel_name = re.sub(pattern, "", str(novel_name))
#簡中轉繁中
novel_name = cv.s2t(novel_name)
return novel_name
def __init__(self, bibItemStr, style="mustAPA"):
"""
初始化
"""
self.gDic = ""
# 初始化时传入的字符转繁体
self.bibitemStr = cv.s2t(bibItemStr)
# 表示 bib文件中每一个item 格式后的文本
self.__bibTex = ""
# 表示参考文献的序号
self.__bibIndex = -1
# bib 字典
self.__bibDict = {
"bibType": "",
"citelabel": "",
"author": "",
"editor": "",
"title": "",
"journal": "",
"volume": "",
"number": "",
"pages": "",
"chapter": "",
"institution": "",
"year": "",
"school": "",
"university": "",
"location": "",
"publisher": "",
"booktitle": "",
"issn": "",
"doi": "",
"type": "",
"organization": "",
"url": "",
"note": "",
"description": "",
"date": ""
}
# 初始化执行 转字典 方法
self.__to_bibDict()
# 获取作者姓名序号
self.__getbibIndex()
# 默认参考文献样式为 MUST APA
if style == "mustAPA":
self.__to_bibStyle_mustAPA()
else:
pass # to do
def get_chapter_content(sub_chapter):
#請求當前章節頁面 params為請求引數
r = requests.get(req_url + chapter_url[sub_chapter], params=req_header)
#soup轉換
soup = BeautifulSoup(r.text, "html.parser")
#以selcetor獲取章節名稱
chapter_name = soup.select(
'#wrapper .content_read .box_con .bookname h1')[0]
pattern = re.compile(r'<(/*)h1>') #移除<h1> & </h1>
chapter_name = re.sub(pattern, "", str(chapter_name))
#獲取章節內容
chapter_text = soup.select('#wrapper .content_read .box_con #content')[0]
#刪去內容不必要的東西
chapter_text = re.sub(r'<br/>', '\n\n',
str(chapter_text)) #移除html的換行符號<br/>
chapter_text = re.sub(r'<div id="content">', '',
str(chapter_text)) #移除此段<div id="content">
chapter_text = re.sub(r'<(/*)div>', '',
str(chapter_text)) #移除<div> & </div>
#簡中轉繁中
chapter_name = cv.s2t(chapter_name)
chapter_text = cv.s2t(chapter_text)
return chapter_name, chapter_text
# -*- coding: utf-8 -*-
"""
__title__ = 'example'
__author__ = 'JieYuan'
__mtime__ = '2018/6/5'
"""
from inlp.convert import char, chinese
from inlp.explode import Strokes, Chars
from inlp.similarity import simhash, thesaurus
print('\n%s\n' % 'inlp.convert')
print(char.half2full("0123456789"))
print(char.full2half("０１２３４５６７８９"))
print(chinese.s2t('忧郁的台湾乌龟')) # chinese.simple2tradition('忧郁的台湾乌龟')
print(chinese.t2s('憂郁的臺灣烏龜')) # chinese.tradition2simple('憂郁的臺灣烏龜')
print('\n%s\n' % 'inlp.explode')
print(Chars().get_chars('袁'))
print(Strokes().get_strokes('袁'))
print('\n%s\n' % 'inlp.similarity')
s1 = ['周杰伦', '是', '一个', '歌手']
s2 = ['刘若英', '是', '个', '演员']
print(simhash(s1, s2))
print(thesaurus.cilin(s1, s2))
print(thesaurus.hownet(s1, s2))
def post_proc(_str):
_str = beautify_str(_str)
return cv.t2s(_str) if lans == 'cn' else cv.s2t(_str)
filepath = ""
bibFilePath = []
bibFileStr = ""
# 搜索所有 tex 文本,将文本内容全转为繁体
for i, j, k in os.walk("."):
for ii in k:
temPath = os.path.join(i, ii)
# 如果找到 tex 后缀的文件
if ".tex" in temPath:
filepath = temPath
with open(filepath, "r+", encoding="utf-8") as f:
# 读取全文
temp = f.read()
# 全文转繁体
temp = cv.s2t(temp)
# 全文重写到文件中
f.seek(0)
f.truncate()
f.write(temp)
# 如果找到 bib 后缀的文件
elif ".bib" in temPath:
bibFilePath.append(temPath)
# 得到格式化的 bib 文件
bibFileStr = iitool.BIBPYITEM.allbibFileToStr(bibFilePath)
# 将格式化的 bib 文本内容转成繁体
bibFileStr = cv.s2t(bibFileStr)
# 對文本進行預處理,(處理一些特殊字符)
bibFileStr = bibFileStr.replace(r"&", r"\&")