def escape_bp_tag(text):
# 转义编排标签
text = red.sub(r'^(<(?:time|mark)>)',
r'#\1',
text,
flags=red.MULTILINE)
# 【引用开始】、【引用结束】
text = red.sub(r'【(引用(?:开始|结束)|补充回复)】', r'[\1]', text)
# 标记的处理信息
if text.endswith('【与上一条回复重复】') \
or text.endswith('【无法处理的回复】'):
text = text + '#'
return text
def bp_to_final(infile, keep_discard=True, label=0):
'''编译 编排to最终、丢弃'''
class placeholder:
def __init__(self, posi=0, pagenum=0, show=False):
self.posi = posi
self.pagenum = pagenum
self.show = show
def is_not_empty(lst):
for i in lst:
yield i.strip() != ''
info_list = list()
holder_list = [placeholder()]
text_list = list()
abandon_list = list()
pickcount, allcount = 0, 0
# 用于把 [img]http://img3.laibafile.cn/p/m/1234567.jpg[/img]
# 替换成 【图片：1234567.jpg】
picr = (r'\[img\s*(\d+|)\].*?\[/img\]')
pattern = red.re_dict(picr)
# 提取页号
re_pagenum = red.re_dict(r'^<page>页号:\s*(\d+)\s*$')
# 提取时间
p_time = (r'^<time>[^<]*<\d\d(\d\d-\d{1,2}-\d{1,2})\s+'
r'(\d{1,2}:\d{1,2})')
re_time = red.re_dict(p_time)
# 读取编排文本
in_reply = False
temp = list()
current_page = 0
current_time = ''
for line in infile.readlines():
if line.startswith('<time>'):
if in_reply == True:
print('格式错误：回复文本的前后包括标志不配对。\n',
'丢失<mark>行')
break
in_reply = True
# current_time
if label == 2:
m = re_time.search(line)
if m:
current_time = m.group(1) + ' ' + m.group(2)
else:
current_time = ''
elif line.startswith('<mark>'):
if in_reply == False:
print('格式错误：回复文本的前后包括标志不配对。\n',
'丢失<time>行')
break
if line.endswith('█\n') or line.endswith('█'):
pickcount += 1
if label == 0:
pass
elif label == 1:
holder_list[-1].show = True
elif label == 2:
floor_label = ('№.%d ☆☆☆'
' 发表于%s P.%d '
'☆☆☆\n'
'-------------------------'
'-------------------------'
'\n')
floor_label = floor_label % \
(pickcount, current_time, current_page)
text_list.append(floor_label)
text_list.extend(temp)
text_list.append('\n')
elif any(is_not_empty(temp)):
abandon_list.extend(temp)
abandon_list.append('∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞∞\n\n')
temp.clear()
allcount += 1
in_reply = False
elif in_reply:
line = pattern.sub(r'【一张图片\1】', line)
temp.append(line)
# 由于上一个elif，以下必定not in_reply
elif not text_list and not abandon_list and \
line.startswith('<tiezi>'):
info_list.append(line[len('<tiezi>'):])
elif label != 0:
m = re_pagenum.search(line)
if m:
current_page = int(m.group(1))
if label == 1:
text_list.append('')
holder = placeholder(len(text_list)-1,
current_page
)
holder_list.append(holder)
infile.close()
if in_reply == True:
print('格式错误：最后一个回复文本的前后包括标志不配对。')
# 页码 辅助格式
if label == 1:
for holder in holder_list[1:]:
if holder.show:
page_label = ('☆☆☆☆☆'
' 进入第%d页 '
'☆☆☆☆☆\n'
'----------------'
'----------------'
'\n\n') % holder.pagenum
text_list[holder.posi] = page_label
color_p1 = color.fore_color(allcount, color.Fore.YELLOW)
color_p2 = color.fore_color(pickcount, color.Fore.YELLOW)
print('共有{0}条回复，选择了其中{1}条回复'.format(color_p1, color_p2))
# output的内容============
# 连接
if info_list:
s_iter = itertools.chain(info_list, '\n', text_list)
else:
s_iter = iter(text_list)
s = ''.join(s_iter)
# 连续的多张图片
s = red.sub(r'(?:【一张图片(\d+|)】\s+){3,}',
r'【多张图片\1】\n\n',
s)
s = red.sub(r'(?:【一张图片(\d+|)】\s+){2}',
r'【两张图片\1】\n\n',
s)
# 输出StringIO
output = StringIO(s)
# 汉字字数
chinese_ct = count_chinese(s)
# 丢弃文本
if keep_discard and abandon_list:
s_iter = itertools.chain(info_list, '\n', abandon_list)
s = ''.join(s_iter)
discard = StringIO(s)
else:
discard = None
return output, discard, info_list, chinese_ct
def doit(self):
# 获取、显示网址
try:
u = self.master.clipboard_get().strip()
except:
bad = True
u = ''
else:
bad = False
if bad or not tz2txt.is_url(u):
self.url.set('无效网址，网址须以http://或https://开头。')
return
self.url.set(u)
# 辅助模式
assist = self.assist.get()
if assist == 1:
label = ''
elif assist == 2:
label = 'page'
elif assist == 3:
label = 'floor'
# 末页
till = self.till.get().strip()
try:
till = int(till)
except:
till = -1
# 执行命令
self.status['fg'] = '#993300'
self.status['text'] = '处理中'
self.update()
# except里return
try:
output, discard_output, title, info_list, chinese_ct = \
tz2txt.auto(u, till, '', '', label, from_gui=True)
if title == None:
raise Exception('无法完成全自动处理')
except Exception as e:
print('\n出现异常：', e)
print('===================================\n')
return
else:
# 显示标题
title = red.sub(r'[\U00010000-\U0010FFFF]', r'', title)
title = title.strip()
self.url.set(title)
finally:
self.status['fg'] = 'blue'
self.status['text'] = '待机'
# 输出文件名
if self.rename.get():
output_fn = title + '.txt'
else:
output_fn = self.output.get().strip()
# 合法文件名
output_fn = red.sub(r'[\\/:*?"<>|]', r'', output_fn)
if output_fn == '.txt':
output_fn = '楼主.txt'
# 输出内容
text = output.getvalue()
output.close()
# 覆盖判断：文件已存在 and 输出有内容 and (强制覆盖 or 选择覆盖)
if os.path.isfile(output_fn) and \
text and \
(self.override.get() == 1 or \
messagebox.askyesno('输出文件已存在', '是否覆盖？\n%s' % output_fn)
):
# 删除已有目标
try:
os.remove(output_fn)
except:
pass
# 写入output
if not os.path.isfile(output_fn) and text:
try:
with open(output_fn, 'w',
encoding='gb18030', errors='replace') as f:
f.write(text)
print('\n已保存为：', output_fn)
except Exception as e:
print('\n保存文件时出现异常', e)
# 显示信息
size2 = os.path.getsize(output_fn)
size2 = format(size2, ',')
chinese_ct = format(chinese_ct, ',')
print('输出文件 {0} 字节，约 {1} 个汉字。'.format(
size2,
chinese_ct)
)
# 写入discard
if discard_output != None:
try:
text = discard_output.getvalue()
discard_output.close()
if text:
with open(discard_fn, 'w',
encoding='gb18030', errors='replace') as f:
f.write(text)
except Exception as e:
print('\n保存文件时出现异常', e)
print()
for line in info_list:
if line.startswith('下载时间：'):
break
datamachine.save_print(line.rstrip('\n'))
print('===================================\n')
def doit(self):
# 获取、显示网址
try:
u = self.master.clipboard_get().strip()
except:
bad = True
u = ''
else:
bad = False
if bad or not tz2txt.is_url(u):
self.url.set('无效网址，网址须以http://或https://开头。')
return
self.url.set(u)
# 辅助模式
assist = self.assist.get()
if assist == 1:
label = ''
elif assist == 2:
label = 'page'
elif assist == 3:
label = 'floor'
# 末页
till = self.till.get().strip()
try:
till = int(till)
except:
till = -1
# 执行命令
self.status['fg'] = '#993300'
self.status['text'] = '处理中'
self.update()
# except里return
try:
output, discard_output, title, info_list, chinese_ct = \
tz2txt.auto(u, till, '', '', label, from_gui=True)
if title == None:
raise Exception('无法完成全自动处理')
except Exception as e:
print('\n出现异常：', e)
print('===================================\n')
return
else:
# 显示标题
title = red.sub(r'[\U00010000-\U0010FFFF]', r'', title)
title = title.strip()
self.url.set(title)
finally:
self.status['fg'] = 'blue'
self.status['text'] = '待机'
# 输出文件名
if self.rename.get():
output_fn = title + '.txt'
else:
output_fn = self.output.get().strip()
# 合法文件名
output_fn = red.sub(r'[\\/:*?"<>|]', r'', output_fn)
if output_fn == '.txt':
output_fn = '楼主.txt'
# 输出内容
text = output.getvalue()
output.close()
# 覆盖判断：文件已存在 and 输出有内容 and (强制覆盖 or 选择覆盖)
if os.path.isfile(output_fn) and \
text and \
(self.override.get() == 1 or \
messagebox.askyesno('输出文件已存在', '是否覆盖？\n%s' % output_fn)
):
# 删除已有目标
try:
os.remove(output_fn)
except:
pass
# 写入output
if not os.path.isfile(output_fn) and text:
try:
with open(output_fn, 'w', encoding='gb18030',
errors='replace') as f:
f.write(text)
print('\n已保存为：', output_fn)
except Exception as e:
print('\n保存文件时出现异常', e)
# 显示信息
size2 = os.path.getsize(output_fn)
size2 = format(size2, ',')
chinese_ct = format(chinese_ct, ',')
print('输出文件 {0} 字节，约 {1} 个汉字。'.format(size2, chinese_ct))
# 写入discard
if discard_output != None:
try:
text = discard_output.getvalue()
discard_output.close()
if text:
with open(discard_fn,
'w',
encoding='gb18030',
errors='replace') as f:
f.write(text)
except Exception as e:
print('\n保存文件时出现异常', e)
print()
for line in info_list:
if line.startswith('下载时间：'):
break
datamachine.save_print(line.rstrip('\n'))
print('===================================\n')