我有這個代碼，它可以找到單詞 |1234| 并復制所有行直到 abcd| 找到，它不會復制包含 abcd| 的行。我想讓這段代碼適用于多個字符串。例如，搜索該行是否包含 |1234| 或 |56789| 或 |54321| 并復制所有包含這些單詞的行，直到行 abcd| （這不會改變）。順便說一句，代碼還將所有 txt 合二為一（我需要搜索多個文件。是否可以修改代碼使其可以搜索多個 start_marker？如何？有人可以幫我嗎？import globimport osclass Collector: def __init__(self, filename, start_marker, stop_marker): self.toggle_collect = False self.f = open(filename, encoding='utf-8', errors='ignore') self.m1 = '|1234|' lf.m2 = 'abcd|' def __enter__ (self): return self def __exit__ (self, exc_type, exc_value, traceback): self.f.close() def __iter__(self): return self def __next__(self): while True: r = next(self.f) if self.m1 in r: # found the start-collecting marker self.toggle_collect = True elif self.m2 in r: # found the stop-collecting marker self.toggle_collect = False continue if self.toggle_collect: # we are collecting return r # .rstrip() # provide rowsrc_path = "e:/teste/Filtrados/"dst_path = "e:/teste/FiltradosFinal/"filelist = (fn for fn in os.listdir(src_path) if fn.endswith(".txt"))for x in filelist: print(f"Processing file {x}") with open(os.path.join(dst_path, x), 'w', encoding='utf-8', errors='ignore') as f, \ Collector(os.path.join(src_path, x), '1234', 'abcd') as c: for r in c: f.write(r)read_files = glob.glob("e:/teste/FiltradosFinal//*.txt")with open("e:/teste/teste.txt", "wb") as outfile: for f in read_files: print("Combinando arquivos") with open(f, "rb") as infile:輸入00000|12333|somethingwordanother_oneabcd|00000|12320|somethingwordanother_oneabcd|00000|12321|somethingwordanother_oneabcd|輸出00000|12333|somethingwordanother_oneabcd|00000|12321|somethingwordanother_oneabcd|我想復制所有，例如，'|12333|' 之間的行 或“|12321|” 直到找到結束標記 abcd|。我的代碼做到了，但只有當我設置一個標記時，我才想要多個開始標記
1 回答
慕姐8265434
TA貢獻1813條經驗 獲得超2個贊
import glob
import os
class Collector:
def __init__(self, filename, start_marker, stop_marker):
self.toggle_collect = False
self.f = open(filename, encoding='utf-8', errors='ignore')
self.m1s = ['|1234|', 'other_word1', 'other_word2']
self.m2 = 'abcd|'
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.f.close()
def __iter__(self):
return self
def __next__(self):
while True:
r = next(self.f)
for m1 in self.m1s:
if self.m2 in r: # found the stop-collecting marker
break
if m1 in r: # found the start-collecting marker
return r # .rstrip() # provide row
src_path = "e:/teste/Filtrados/"
dst_path = "e:/teste/FiltradosFinal/"
filelist = (fn for fn in os.listdir(src_path) if fn.endswith(".txt"))
for x in filelist:
print(f"Processing file {x}")
with open(os.path.join(dst_path, x), 'w', encoding='utf-8', errors='ignore') as f, \
Collector(os.path.join(src_path, x), '1234', 'abcd') as c:
for r in c:
f.write(r)
read_files = glob.glob("e:/teste/FiltradosFinal//*.txt")
with open("e:/teste/teste.txt", "wb") as outfile:
for f in read_files:
print("Combinando arquivos")
with open(f, "rb") as infile:
我沒有測試代碼，因為您沒有提供任何方便的輸入或所需的輸出，但這似乎可以滿足您的要求。
我建議使用有意義的名稱而不是m1and m2，這樣您就可以在代碼變大時調試自己的代碼（更不用說讓其他人閱讀它了）。
添加回答
舉報
0/150
提交
取消