diff --git a/list_key_finder.py b/list_key_finder.py new file mode 100644 index 0000000..f80d8a7 --- /dev/null +++ b/list_key_finder.py @@ -0,0 +1,25 @@ +import re + +search = ["教学", "套路"] + +rf = open("result.txt", "w", encoding="gbk") + +with open("a.txt", "r", encoding="gbk") as f: + content = f.read(1 << 20) + result = re.findall(r"^(?P[^\t\r\n]+)\t(?P<content>[^\t]+)\t(?P<aid>\d+)\t(?P<bvid>BV[^\t\r\n]+)$", content, + re.MULTILINE) + for item in result: + title, content, aid, bvid = item + matched = [] + for line in content.split("\n"): + for key in search: + if key in line: + matched.append(line) + if len(matched) > 0: + rf.write("\n".join([ + title, + *matched, + "", + "", + ])) +rf.close() \ No newline at end of file