如何使用 jieba 断词工具的 jieba.suggest_freq 设定 URL 不被切开（设定字串范围）

好像 jieba.suggest_freq 并没有提供正则式的功能, 提供自己写的两个函数, 试试.

from datetime import date,datetime
import csv
import codecs
import time
import re
import sys
import os
import jieba
from itertools import repeat

def url_split(string, sep=['https://', 'http://'], end=' '):
    if not string:
        return []
    if not any(map(str.__contains__, repeat(string), sep)):
        return [string]
    items = []
    for head in sep:
        try:
            start_ = string.index(head)
            items.append(start_)
        except:
            pass
    start = min(items)
    try:
        stop = string.index(end, start)
    except:
        stop = len(string)
    return [string[:start], string[start:stop]] + url_split(string[stop:])

def cut_all(sequence):
    result = []
    for item in sequence:
        result += [item] if any(map(str.startswith, repeat(item), sep)) else jieba.cut(item)
    return result

sep = ['https://', 'http://']
end = ' '
jieba.load_userdict('./data/dict.txt')
jieba.suggest_freq('李嘉誠',True)

file_name = 'head300.csv'

with open (file_name, 'r', encoding="utf-8") as csvfile:
    reader = csv.reader(csvfile)
    column = [row[4] for row in reader]

print(f"Total: {len(column)}")

for item in column:
    print(item)
    content_output = cut_all(url_split(item))
    print_list = '/'.join(content_output) + '\n'
    with open('seg.csv', 'a', newline='', encoding='utf-8') as csvfile:
        csvfile.write(print_list)
    print(print_list)

內定就是侦测第一个空白格, 我试了一下, OK啊

column = ['光绪年间有这样一个真实的故事。 https://ibook.idv.tw/enews/enews1531-1560/enews1536.html 江苏的贾先生，在上海租界一洋行工作，深得老板信任。 https://ibook.idv.tw/enews/enews1531-1560/enews1536.html 端午节前，老板派他去城南一带收欠款，他带上皮袋子就出发了。 ']
print(f"Total: {len(column)}")

for item in column:
    # print(item)
    content_output = cut_all(url_split(item))
    print_list = '/'.join(content_output) + '\n'
    #with open('seg.csv', 'a', newline='', encoding='utf-8') as csvfile:
    # csvfile.write(print_list)
    print(print_list)

Total: 1
光绪/年间/有/这样/一个/真实/的/故事/。 /https://ibook.idv.tw/enews/enews1531-1560/enews1536.html/ /江苏/的/贾/先生/，/在/上海/租界/一/洋行/工作/，/深得/老/板/信任/。 /https://ibook.idv.tw/enews/enews1531-1560/enews1536.html/ /端午/节前/，/老/板/派/他/去/城南/一带/收/欠款/，/他/带/上/皮袋子/就/出发/了/。