def filter(text, result_file=None):
p_word = re.compile(r'([，。？]?)(.+?)\((.+?)\)')
for line in text.split('\n'):
word_list = list()
pinyin_list = list()
line = line.strip()
match_list = re.findall(p_word, line)
for match in match_list:
symbol, word, pinyin = match
if symbol:
# 添加标点符号
word_list.append(symbol)
pinyin_list.append(symbol)
if len(word) > 1:
split_pinyin_list = PinyinSplitter.split_pinyin(pinyin)
if len(word) != len(split_pinyin_list):
print('汉字与拼音长度不匹配')
print(match)
return
# 添加多个字
word_list.extend(word)
pinyin_list.extend(split_pinyin_list)
else:
# 添加一个字
word_list.append(word)
pinyin_list.append(pinyin)
string = '\t'.join(['%5s' % i for i in pinyin_list])
print(string)
if result_file:
filex.write(result_file, string + '\n', mode='a')
string = '\t'.join(['%5s' % i for i in word_list])
if result_file:
filex.write(result_file, string + '\n', mode='a')
print(string)
def translate(en):
js = Py4Js()
tk = js.getTk(en)
tk2 = get_google_tk(en)
if tk != tk2:
print('计算的 tk 不相等')
filex.write('data/error_tk.txt', en + '\n', 'a')
return en
url = "http://translate.google.cn/translate_a/single?client=t" \
"&sl=en&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca" \
"&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1" \
"&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s&q=%s" % (tk, urllib.parse.quote(en))
result = netx.get(url, need_print=False)
"""
[[["测试","test",null,null,2],[null,null,"Cèshì","test"]],...]
"""
if result:
result = json.loads(result)
if result:
# 第一个结果
first_result = result[0]
# 前几个为翻译，最后 1 个可能带拼音
cn = ''
for translation in first_result:
if len(translation) == 5:
# 翻译中的第一个即是结果
cn += translation[0]
cn = GoogleTranslator.process_result(en, cn)
return cn
return None
def get_pan_url(self, url):
url = 'http://www.57fx.com' + url
r = requests.get(url)
soup = BeautifulSoup(r.text, "html.parser")
a = soup.find('a', {'name': 'downurl'})
href = a['href']
filex.write(self.pan_list_file, href + '\n', mode='a')
def export_html(source_file, result_file):
"""导出 html"""
lipstick_type = os.path.splitext(os.path.basename(result_file))[0].split('_')[0]
current_path = os.path.dirname(result_file) + '/'
lines = filex.read_lines(source_file, ignore_line_separator=True)
length = len(lines)
html = '''
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>选呀选呀选口红~</title>
<link rel="stylesheet" href="https://cdn.bootcss.com/bootstrap/3.3.7/css/bootstrap.min.css"
integrity="sha384-BVYiiSIFeK1dGmJRAkycuHAHRg32OmUcww7on3RYdg4Va+PmSTsz/K68vbdEjh4u" crossorigin="anonymous">
<link rel="stylesheet" href="css/lipstick.css">
</head>
<body>
<div class="container-fluid">
[content]
</div>
</body>
</html>
'''
content = list()
for i in range(length):
content.append('<div class="row">')
lipstick = Lipstick.from_string(lines[i])
# 左边
content.append('<div class="%s">' % 'col-xs-3')
item_list = ['编号:' + lipstick.index, '色号:' + lipstick.name, '类别:' + lipstick.category, lipstick.other]
for cell in item_list:
content.append('<h4>%s</h4>' % cell)
content.append('</div>')
# 右边的图
image_list = lipstick.img.split(',')
length = len(image_list)
for j in range(length):
if length == 2:
if j == 0:
col_style = 'col-xs-3'
else:
col_style = 'col-xs-5'
else:
col_style = 'col-xs-3'
img = image_list[j]
image_path = '%simage/%s_%03d_%d.jpg' % (current_path, lipstick_type, i + 1, j + 1)
ima_tag = '<img class="%s" src="%s"/>' % (col_style, image_path.replace(current_path, ''))
if not os.path.exists(image_path):
netx.get_file(img, image_path)
content.append(ima_tag)
content.append('</div>')
content = html.replace('[content]', '\n'.join(content))
filex.write(result_file, content)
def export_color_html(source_file, result_file):
"""导出 html"""
html = '''
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>选呀选呀选口红~</title>
<link rel="stylesheet" href="https://cdn.bootcss.com/bootstrap/3.3.7/css/bootstrap.min.css"
integrity="sha384-BVYiiSIFeK1dGmJRAkycuHAHRg32OmUcww7on3RYdg4Va+PmSTsz/K68vbdEjh4u" crossorigin="anonymous">
<link rel="stylesheet" href="css/lipstick_color.css">
</head>
<body>
<div class="container-fluid">
[content]
</div>
</body>
</html>
'''
lipstick_type = os.path.splitext(os.path.basename(result_file))[0].split('_')[0]
content = list()
lines = filex.read_lines(source_file, ignore_line_separator=True)
length = len(lines)
for i in range(0, length, 4):
content.append('<div class="row">')
end_index = i + 4
if end_index > length:
end_index = length
for j in range(i, end_index):
lipstick = Lipstick.from_string(lines[j])
name_tag = '<span class="item">%s</span>' % '<br/>'.join(
('编号:' + lipstick.index, '色号:' + lipstick.name))
image_path = 'image/%s_%03d_%d.jpg' % (lipstick_type, j + 1, 1)
img_tag = '<img class="center-block" src="%s"/>' % image_path
content.append('<div class="col-xs-3">')
content.append(name_tag)
content.append(img_tag)
content.append('</div>')
content.append('</div>')
html = html.replace('[content]', '\n'.join(content))
filex.write(result_file, html)
def export_all_cmd_help(self):
"""导出所有命令的帮助"""
cmd_list = self.get_all_cmd()
length = len(cmd_list)
for i in range(length):
print('%d/%d' % (i + 1, length))
cmd = cmd_list[i]
if ' ' not in cmd:
continue
cmd, info = cmd.split(' ', maxsplit=1)
filex.write(self.all_cmd_file,
'\n\n# 【%d/%d】%s\n' % (i + 1, length, cmd),
mode='a')
if cmd == 'SC':
# 这个要输入，卡住了
continue
cmd = 'help %s > %s' % (cmd, self.temp_file)
self.run_cmd(cmd)
result = filex.read_lines(self.temp_file, encoding='gbk')
result.insert(0, '```\n')
result.append('\n```')
filex.write_lines(self.all_cmd_file, result, mode='a')
os.remove(self.temp_file)
def login(self, file_path):
"""登录并保存信息"""
lines = filex.read_lines(file_path, ignore_line_separator=True)
if not lines:
print('没有读取到登录信息', file_path)
exit()
if len(lines) < 2:
print('登录信息不完整，第一行写帐号，第二行写密码')
exit()
print('打开登录页...')
r = requests.get(self.login_url)
cookies, authenticity_token = self.parse_cookies_and_token_from_result(
r)
if not (cookies and authenticity_token):
print('登录失败')
return
# 获取完 cookies, token ，开始登录
params = {
'username': lines[0],
'password': lines[1],
'utf8': '✓',
'authenticity_token': authenticity_token,
}
print('登录帐号 %s ...' % lines[0])
r = requests.post(self.login_url, params, cookies=cookies)
# 注意 cookies 和 token 都要重新获取
cookies, authenticity_token = self.parse_cookies_and_token_from_result(
r)
if not (cookies and authenticity_token):
print('登录失败')
return
print('登录成功')
cookies_str = ';'.join([k + '=' + v for k, v in cookies.items()])
filex.write(self.cookies_file, cookies_str)
filex.write(self.token_file, authenticity_token)