def FileWithLink():
import time, os, MyDef
start_time = time.time() # 初始时间戳
# ========================输入区开始========================
output_readline = []
refer_file_path = '/Users/alicewish/Dropbox/漫画图源MD5表.csv'
MD5_dict = MyDef.ReadDictC(refer_file_path, True)
yun_link_file_path = '/Users/alicewish/Dropbox/漫画图源度盘地址表.csv'
yun_link_dict = MyDef.ReadDictB(yun_link_file_path)
file_path_list = []
for key in MD5_dict:
file_path = MD5_dict[key]
file_size = os.path.getsize(file_path)
readable_file_size = sizeof_fmt(file_size)
file_name = os.path.split(file_path)[1]
file_path_list.append(file_path)
if file_path in yun_link_dict:
yun_link = yun_link_dict[file_path]
output_line = "[" + file_name + "](" + yun_link + ") | " + readable_file_size
else:
output_line = "[" + file_name + "]() | " + readable_file_size
print(file_name)
# print(output_line)
output_readline.append(output_line)
output_readline.sort()
output_readline.insert(0, '--- | ---')
output_readline.insert(0, '文件名 | 大小')
for i in range(len(output_readline)):
line = output_readline[i]
if "]()" in line:
line = line[1:].replace("]()", "")
output_readline[i] = line
# ================写入剪贴板================
output_text = '\r\n'.join(output_readline)
MyDef.WriteClip(output_text)
print(MyDef.RunTime(start_time))
def Processing():
import time, jieba, re, MyDef
start_time = time.time() # 初始时间戳
scenario_list_full = Training()
# ======================================处理区开始======================================
dict_file_path = '/Users/alicewish/我的坚果云/userdict.txt' # 自定义词典路径
cut_right_count = 0
cut_wrong_count = 0
# ========================输入区开始========================
input_file_path = "/Users/alicewish/Downloads/my.md"
# ================按行读取输入文本================
read_text = open(input_file_path, 'r').read() # 读取文本
text_readline = read_text.replace("\nclass",
"class").replace("...",
"…").splitlines()
# print(text_readline)
# ================按行读取文本:with open(更好)================
status_readline = [] # 状态列表
output_readline = [] # 输出列表
jieba.load_userdict(dict_file_path)
line_formmat_list_all = []
for a in range(len(text_readline)):
text_readline[a] = re.sub(r'<span.*</span>', '',
text_readline[a]) # 去除span
text_readline[a] = text_readline[a].replace('……', '…')
markdown_line = text_readline[a].replace("\*", "の").replace(
"\[", "[").replace("\]", "]")
print(markdown_line)
line_cut_list = markdown_line.split("*")
print(line_cut_list)
plain_line = markdown_line.replace("*", "").replace("の", "*") # 调整*
print(plain_line)
line_formmat_list = []
for j in range(len(plain_line)):
line_formmat_list.append(0)
# print(line_formmat_list)
line_mark_count_list = []
for k in range(len(plain_line) + 1):
line_mark_count_list.append(0)
point = 0
for char in markdown_line:
if char == '*':
line_mark_count_list[point] = line_mark_count_list[point] + 1
else:
point = point + 1
print(line_mark_count_list)
pin = 0
before = 0
for seg in line_cut_list:
if seg == '':
pass
else:
last_pin = pin
pin += len(seg)
# print(line_mark_count_list[last_pin])
# print(line_mark_count_list[pin])
if last_pin > 0:
before = line_formmat_list[last_pin - 1]
for l in range(last_pin, pin):
if before == 0:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 1 and line_mark_count_list[last_pin] == 1:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
elif before == 1 and line_mark_count_list[last_pin] == 2:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 2 and line_mark_count_list[last_pin] == 1:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 2 and line_mark_count_list[last_pin] == 2:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
elif before == 3:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
# print(line_formmat_list[last_pin - 1])
print(line_formmat_list)
line_formmat_list_all.append(line_formmat_list)
print(plain_line)
print(len(plain_line))
need_cut = True # 需要切吗?
if len(plain_line) == 0:
pass
elif len(plain_line) == 2 and re.match(r'[0-9][0-9]', plain_line):
# 页码
need_cut = False
elif a < 8:
# 首部
need_cut = False
elif len(plain_line) > 2:
if plain_line[0] == '*' or plain_line[0] == '[':
# 注释
need_cut = False
if plain_line == "":
status = 0 # 空行
elif not need_cut:
status = -1 # 不需要切
else:
status = 1 # 待分词
status_readline.append(status)
if status == 1:
# ================结巴分词================
string_list = []
seg_list = jieba.cut(plain_line) # 默认是精确模式
for word in seg_list:
string_list.append(word)
print(string_list)
start_status = False
for i in range(len(scenario_list_full)):
scenario_line_full = scenario_list_full[i]
if scenario_line_full[0:2] == str(len(plain_line)).zfill(2):
if start_status:
end_i = i
else:
start_i = i
start_status = True
end_i = i
# ================进行切分================
current_i = start_i
cut_right = False
while current_i <= end_i and not cut_right:
current_cut = scenario_list_full[current_i]
current_cut_list = current_cut[7:].split("-") # 列表存储的切分方案
# ================进行分词判断================
line_can_cut_list = []
for i in range(len(plain_line)):
line_can_cut_list.append(0)
j = 0
for string in string_list:
j = j + len(string)
# print(j)
line_can_cut_list[j - 1] = 1
# ================对标点和语气词进行纠正================
for i in range(len(plain_line)):
if plain_line[i] in ',.?!，。…？！”·-》>:】【]、':
# 这些之前不可切
line_can_cut_list[i - 1] = 0
elif plain_line[i] in '“《<【[':
# 这些之后不可切
line_can_cut_list[i] = 0
elif plain_line[
i] in '上中下内出完的地得了吗吧着个就前世里嘛图们来呗' and line_can_cut_list[
i - 1] == 1 and line_can_cut_list[i] == 1:
# 这些之前不可切
line_can_cut_list[i - 1] = 0
elif plain_line[i] in '太每帮跟另' and line_can_cut_list[
i - 1] == 1 and line_can_cut_list[i] == 1:
# 这些之后不可切
line_can_cut_list[i] = 0
print(line_can_cut_list)
print(current_cut_list)
# ================判断方案正确与否================
sum = 0
cut_right = True
for i in range(len(current_cut_list)): # 切分
last_sum = sum
sum = sum + int(current_cut_list[i])
print(line_can_cut_list[sum - 1])
print(plain_line[last_sum:sum])
if line_can_cut_list[sum - 1] == 0:
cut_right = False
print(cut_right)
if not cut_right:
current_i += 1
if cut_right: # 切对了
cut_right_count += 1
sum = 0
for i in range(len(current_cut_list)):
last_sum = sum
sum = sum + int(current_cut_list[i])
output_line = plain_line[last_sum:sum]
output_line_format_list = line_formmat_list_all[a][
last_sum:sum]
output_line_mark_count_list = []
format_list_for_use = [0] + output_line_format_list + [
0
] # 11
for b in range(len(format_list_for_use) - 1):
output_line_mark_count = abs(format_list_for_use[b +
1] -
format_list_for_use[b])
output_line_mark_count_list.append(
output_line_mark_count)
print(output_line_mark_count_list) # 10
output_markdown_line = ''
for c in range(len(output_line_mark_count_list) - 1):
for d in range(output_line_mark_count_list[c]):
output_markdown_line += '*'
output_markdown_line += output_line[c]
for d in range(output_line_mark_count_list[-1]):
output_markdown_line += '*'
output_readline.append(output_markdown_line)
print("格式", output_line_format_list)
else: # 切错了
output_readline.append(text_readline[a])
cut_wrong_count += 1
elif status == 0: # 不需要切
output_readline.append('\n|\n')
else: # 不需要切
output_readline.append(text_readline[a].replace("\[", "[").replace(
"\]", "]"))
print('切对', cut_right_count)
print('待切', cut_wrong_count)
# ================写入剪贴板================
text = '\r\n'.join(output_readline)
MyDef.WriteClip(text)
print(MyDef.RunTime(start_time))
all_count = len(output_readline) - 1
print(all_count)
text = '\r\n'.join(output_readline)
# print(text)
output_file_name = '0 Day Week文件地址-墨问非名制作-' + now_date + '(' + str(
all_count) + ').csv'
output_file_path = os.path.join(dropbox_path, output_file_name)
f = open(output_file_path, 'w')
try:
f.write(text)
finally:
f.close()
# ================写入剪贴板================
markdown_text = '\r\n'.join(markdown_readline)
MyDef.WriteClip(markdown_text)
# ================运行时间计时================
run_time = time.time() - start_time
if run_time < 60: # 秒(两位小数)
print("耗时:{:.2f}秒".format(run_time))
elif run_time < 3600: # 分+秒(取整)
print("耗时:{:.0f}分{:.0f}秒".format(run_time // 60, run_time % 60))
else: # 时分秒取整
print("耗时:{:.0f}时{:.0f}分{:.0f}秒".format(run_time // 3600,
run_time % 3600 // 60,
run_time % 60))