def space_file(file):
f = open(file, 'r')
txt = f.read()
f.close()
# new_txt = txt.replace('- ', '+ ')
new_txt = txt.replace('* ', '+ ')
# print(new_txt)
f = open(file, 'w')
f.write(new_txt)
f.close()
name, ext = os.path.splitext(file)
nf = open(f'../new_{file}', 'w')
with open(file, 'r') as f:
for line in f.readlines():
tmp = line.strip()
tmp = tmp.replace('blob/debug', 'blob/master')
new = pangu.spacing_text(tmp)
new = new.replace('** ', '**')
new = new.replace(' **', '**')
new = new.replace('~~ ', '~~')
new = new.replace(' ~~', '~~')
nf.writelines(new + '\n')
# print(new)
nf.close()
def clearReplace(self, text):
paragraph = []
multi_replace_regexp = re.compile(r'\n\s*\n')
text_segment = multi_replace_regexp.split(text)
period_replace_regexp = re.compile(r'\n')
for i in text_segment:
line_i = i.strip()
if self.flag_keep_period_replace == 1:
line_tmp = []
line_segment = period_replace_regexp.split(line_i)
for j in line_segment:
line_j = j.strip()
if re.match(r'.*[.:?!。：？！]$', line_j):
line_tmp.append(line_j)
line_tmp.append('\n')
else:
line_tmp.append(line_j)
line_tmp.append(' ')
paragraph.append(''.join(line_tmp))
else:
paragraph.append(line_i.replace('\n', ' '))
fine_text = '\n\n'.join(paragraph) # 多次换行保留为直接换两行
new_text = pangu.spacing_text(fine_text)
return new_text
def highlight(text: str, keyword: str):
text = pangu.spacing_text(text)
return re.sub(
keyword,
"\33[0m" + "\33[93m" + keyword + "\33[0m" + "\33[37m",
text,
flags=re.IGNORECASE,
)
def headersstr2headers(header_str):
t = arrow.now()
print('大家好，今天是公历 %d 月 %d 日，星期%s \r\n' %
(t.month, t.day, week[t.weekday()]))
for str_line in header_str.splitlines():
if str_line != "":
str_line = re.sub('\.$', '。', str_line)
str_line = re.sub('。$', '', str_line)
pangu_text = pangu.spacing_text(str_line)
print(pangu_text + '\r\n')
def youdao_api(words: str):
print()
print(huepy.grey(" -------- "))
print()
url = (
"http://fanyi.youdao.com/openapi.do?keyfrom={}&key={}&"
"type=data&doctype=json&version=1.1&q={}"
)
try:
resp = requests.get(
url.format(CONF.youdao_key_from, CONF.youdao_key, words), headers=HEADERS
).json()
phonetic = ""
basic = resp.get("basic", None)
if basic and resp.get("basic").get("phonetic"):
phonetic += huepy.purple(" [ " + basic.get("phonetic") + " ]")
print(" " + words + phonetic + huepy.grey(" ~ fanyi.youdao.com"))
print()
translation = resp.get("translation", [])
if len(translation) > 0:
print(" - " + pangu.spacing_text(huepy.green(translation[0])))
if basic and basic.get("explains", None):
for item in basic.get("explains"):
print(huepy.grey(" - ") + pangu.spacing_text(huepy.green(item)))
print()
web = resp.get("web", None)
if web and len(web):
for i, item in enumerate(web):
print(
huepy.grey(
" " + str(i + 1) + ". " + highlight(item.get("key"), words)
)
)
print(" " + huepy.cyan(", ".join(item.get("value"))))
except:
print(" " + huepy.red(ERR_MSG))
def on_pangu_btn_clicked(self):
text = self.before_txt.toPlainText()
if text:
text = self.handle_text(text)
try:
text = pangu.spacing_text(text)
except:
pass
self.after_txt.setText(text)
def to_html(data, template_filename, fp):
# Template with Jinja2
with _resources.path("crawler_book_info", "templates") as _path:
template_path = str(_path)
loader = FileSystemLoader(searchpath=template_path)
env = Environment(loader=loader)
template = env.get_template(template_filename)
# Mapping the parser data to template.
result = template.render(**data)
# Write to HTML file.
fp.write(pangu.spacing_text(result))
def google_api(words: str):
print()
def switch_language():
for w in words:
if "\u4e00" <= w <= "\u9fff":
return "en"
return "zh-cn"
translator = Translator(service_urls=["translate.google.cn"])
text = pangu.spacing_text(translator.translate(words, dest=switch_language()).text)
print(" " + words + huepy.grey(" ~ translate.google.cn"))
print()
print(" - " + huepy.cyan(text))
def modify_text(line):
"""处理文字的格式"""
# 去 \n 是转 pdf 时启用
# line = line.replace('\n', '')
line = pangu.spacing_text(line)
new_line = line.replace(' “', '“')\
.replace('” ', '”')\
.replace('“', '「')\
.replace('”', '」')\
.replace('・', '·')\
.replace('， ', '，')\
.replace('。 ', '。')\
.replace('’', '\'')\
.replace(' ', ' ')
new_line = new_line.strip()
return new_line
def parse_html(content):
content = content.replace("\n", "<br>")
result = re.findall(r"<e [^>]*>", content)
if result:
for i in result:
html = PyQuery(i)
if html.attr("type") == "web":
template = "[%s](%s)" % (parse.unquote(
html.attr("title")), parse.unquote(html.attr("href")))
elif html.attr("type") == "hashtag":
template = " `%s` " % parse.unquote(html.attr("title"))
elif html.attr("type") == "mention":
template = parse.unquote(html.attr("title"))
else:
template = i
content = content.strip().replace(i, template)
else:
content = pangu.spacing_text(content)
return content
def onClipboradChanged(self):
"""
根据是否 `监听剪贴板` 和 `自动替换回车`
"""
if not self.listen_clip_board.isChecked():
return
clipboard = QApplication.clipboard()
text = clipboard.text()
if not text:
return
text = self.handle_text(text)
self.before_txt.setText(text)
try:
text = pangu.spacing_text(text)
except:
pass
self.after_txt.setText(text)
def parse_html(self, content):
content = content.replace("\n", "<br>")
result = re.findall(r"<e [^>]*>", content)
if result:
for i in result:
html = PyQuery(i)
if html.attr("type") == "web":
title = parse.unquote(html.attr("title"))
url = parse.unquote(html.attr("href"))
template = "[%s](%s)" % (title, url)
template += f"\n## {title}\n"
template += self.parse_article(url)
template += "\n"
elif html.attr("type") == "hashtag":
template = " `%s` " % parse.unquote(html.attr("title"))
elif html.attr("type") == "mention":
template = parse.unquote(html.attr("title"))
else:
template = i
content = content.strip().replace(i, template)
else:
content = pangu.spacing_text(content)
return content
def format_python(self, text):
return FormatCode(pangu.spacing_text(text))[0]
def format_md(self, text):
return pangu.spacing_text(text)
def format_json(self, text):
return jsbeautifier.beautify(pangu.spacing_text(text))
runpy3 () {
/anaconda3/bin/python << 'EOF' - "$@"
import sys
import pangu
import clipboard
import pyautogui
for f in sys.argv:
target = clipboard.paste()
result = pangu.spacing_text(target)
clipboard.copy(result)
pyautogui.keyDown('command')
pyautogui.press('v')
pyautogui.keyUp('command')
EOF
}
runpy3 "$@"
def get_html_from_blog(self, blog, rule):
s = requests.session()
r = s.get(blog.url, headers=headers)
if rule['encoding'] is not None:
r.encoding = 'utf-8'
# 获取文本内容
html = r.text
soup = BeautifulSoup(html, 'lxml')
if False:
# 增加代码标签
html = re.sub('<code.*?>', '<code>```\n', html)
html = re.sub('</code>', '```\n</code>', html)
with open('temp.html', 'w', encoding='utf-8') as f:
f.write(html)
# 正则获取标题
title_pattern = rule['title_pattern']
titles = re.findall(title_pattern, html, re.DOTALL)
if len(titles) == 0:
title = 'default'
else:
title = pangu.spacing_text(titles[0])
blog.title = title
print('标题:', title)
if rule['content_type'] == 'bs':
content = soup.select(rule['content_pattern']).pop()
content = str(content)
else:
# 提取正文内容
content_pattern = rule['content_pattern']
contents = re.findall(content_pattern, html, re.DOTALL)
if len(contents) == 0:
content = ''
else:
content = contents[0]
content = '<h1><a href="{}">{}</a></h1><br><br>'.format(
blog.url, blog.title) + content
for src, dst in rule['content_replaces']:
content = re.sub(src, dst, content)
blog.content = content
# print('正文:', content)
# 转换为 MD
# md_content = Tomd(content).markdown
# content = re.sub('<a id=".*?"></a>', '', content)
text_maker = ht.HTML2Text()
md_content = text_maker.handle(content)
# 去空行
md_content = md_content.replace('\r', '')
while ' \n' in md_content:
md_content = md_content.replace(' \n', '\n')
#md_content = md_content.replace('\n', '\n\n')
while '\n\n\n' in md_content:
md_content = md_content.replace('\n\n\n', '\n\n')
# print(' MD:', md_content)
# 正则替换
for src, dst in rule['md_replaces']:
md_content = re.sub(src, dst, md_content)
# 加空格
md_content = pangu.spacing_text(md_content)
# ** *
for star_line in re.findall('\*(.*?)\*', md_content):
md_content = md_content.replace('{}'.format(star_line),
'{}'.format(star_line.strip()))
# 异常断行
md_content = re.sub('-\n', '-', md_content)
# 规范代码标签
#md_content = re.sub('[ ]```', '```', md_content)
# 过滤非法字符
title = re.sub('[\/:*?"<>|]', '-', title)
with open("blogs" + os.sep + title + '.md', 'w',
encoding='utf-8') as f:
f.write(md_content)
pass
def main():
try:
# Template with Jinja2
template = Template('''\
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width" />
<title> {{ title }} </title>
</head>
<body>
<p>
Buy:
<ul>
<li> <a href="{{ url }}" target="_blank">博客來</a> </li>
</ul>
</p>
<hr>
{{ full_title }}
<p>
<img src="{{ cover }}"/>
</p>
{{ info1 }}
{{ price }}
{{ info2 }}
<h2>商品描述</h2>
{{ desc }}
<h2>作者簡介</h2>
{{ author }}
<h2>目錄大綱</h2>
{{ outline }}
<h2>Memo</h2>
<h3>我想讀這本書的原因是什麼?</h3>
<ol>
<li> <FIXED_ME> </li>
</ol>
<h3>看完書封介紹和目錄大綱後，我覺得我可以從那邊得到什麼?</h3>
<ol>
<li> <FIXED_ME> </li>
</ol>
<h3>在買這本新書前，我曾讀過相關的主題的書籍嗎? 當時得到了什麼新知?</h3>
<ol>
<li> <FIXED_ME> </li>
</ol>
<footer style="text-align: center;">
Parser by
<a href="https://github.com/chusiang/crawler-book-info" target="_blank">
chusiang/crawler-book-info
</a>
<hr>
</footer>
</body>
</html>
''')
# Get data.
data = get_data()
# Parser.
book_title = parser_book_title(data[0])
book_url = data[1]
book_full_title = parser_book_full_title(data[0])
book_cover = parser_book_cover(data[0])
book_info1 = parser_book_info1(data[0])
book_price = parser_book_price(data[0])
book_info2 = parser_book_info2(data[0])
book_desc = parser_book_desc(data[0])
book_author = parser_book_author(data[0])
book_outline = parser_book_outline(data[0])
# Mapping the parser data to template.
result = template.render(
title=book_title,
url=book_url,
full_title=book_full_title,
cover=book_cover,
info1=book_info1,
price=book_price,
info2=book_info2,
desc=book_desc,
author=book_author,
outline=book_outline
)
# Write to HTML file.
f = open('index.html', 'w')
f.write(pangu.spacing_text(result))
f.close()
except Exception as e:
print(e)
def pangu_func(self, keyword):
text = pyperclip.paste()
new_text = pangu.spacing_text(text)
pyperclip.copy(new_text)
def format_sql(self, text):
return sqlparse.format(pangu.spacing_text(text))
for infile in glob.glob("/Users/Daglas/Desktop/*.docx"):
filename, ext = os.path.splitext(infile)
document = Document(filename + ".docx")
# document.save('new-file-name.txt')
# for para in document.paragraphs:
# print(para.text)
# 对文字处理并写入文件
with open(filename + ".md", 'w') as file_obj:
for para in document.paragraphs:
if para.text != '\n':
file_obj.write(para.text + "\n\n")
# 读取文件，文件名「filename + ".md"」是关键
with open(filename + ".md") as file_obj:
lines = file_obj.readlines()
with open(filename + ".md", 'w') as file_obj:
for line in lines:
if line != '\n':
new_content = pangu.spacing_text(line)
new_content = new_content.replace(' “', '“')
new_content = new_content.replace('” ', '”')
new_content = new_content.replace('“', '「')
new_content = new_content.replace('”', '」')
new_content = new_content.replace('・', '·')
new_content = new_content.replace('， ', '，')
new_content = new_content.replace('。 ', '。')
file_obj.write(new_content + "\n\n")
def cjk_layout(text):
return pangu.spacing_text(text)
def test_spacing_text(self):
self.assertEqual(pangu.spacing_text('請使用uname -m指令來檢查你的Linux作業系統是32位元或是[敏感词已被屏蔽]位元'), '請使用 uname -m 指令來檢查你的 Linux 作業系統是 32 位元或是 [敏感词已被屏蔽] 位元')
async def set_content(self, content):
return await self.set_props_by_key('content',
pangu.spacing_text(content))
#!/usr/bin/python3 # coding=utf-8 import pangu import pyperclip text = pyperclip.paste() print(text) new_text = pangu.spacing_text(text) pyperclip.copy(new_text) print(new_text)
def pangu_spacing(self):
self.text = pangu.spacing_text(self.text)
return self
#!/usr/bin/python3
# -*- coding: utf-8 -*-
import pangu
import pyperclip
import sys
from enum import Enum, unique
@unique
class QueryMode(Enum):
Paste = 0 # 格式化剪切板文字
Selection = 1 # 格式化选中文字
mode = QueryMode.Selection
query = ""
if sys.argv[1]:
mode = QueryMode.Selection
query = sys.argv[1]
else:
mode = QueryMode.Paste
query = pyperclip.paste()
ret = pangu.spacing_text(query)
if mode == QueryMode.Selection:
print(ret, end='') # 默认输出不要换行
else:
pyperclip.copy(ret)
def wrapper(*args, **kwargs):
_args = list(args)
_args[index] = pangu.spacing_text(_args[index])
result = func(*_args, **kwargs)
return result
arr.append('。')
arr.append('？')
arr.append('！')
arr.append(',')
arr.append('.')
arr.append('?')
arr.append('!')
if sys.argv[2] == 'all':
replace = sys.argv[3]
else:
replace = sys.argv[2]
sub = "[" + "|".join(arr) + "]+"
f1 = open(script, 'r')
lines = f1.readlines()
for line in lines:
if line.strip() == '':
continue
data = re.split('[\t ]', line)
trans = ' '.join(data[1:])
new = re.sub(sub, replace, trans) \
.replace('[', replace) \
.replace(']', replace) \
.replace('FIL', replace) \
.replace('SPK', replace) \
.replace(' ', ' ')
print(data[0] + '\t' + pangu.spacing_text(new).upper().strip())
f1.close()
