ptt_stock

from PttWebCrawler.crawler import *
import json
import re

# change here
message_filters = ['今天','什麼','還是']
article_id = 'M.1609135202.A.69E'

c = PttWebCrawler(as_lib=True)
c.parse_article(board='Stock',article_id=article_id)
f = open('Stock-'+article_id+'.json',)
article = json.load(f)

#message to string
all_message = ''
for message in article['messages']:
    all_message = message['push_content'] +' '+ all_message
    
#filter
all_message = re.sub(r'http\S+', '', all_message)
for message_filter in message_filters:
    all_message = all_message.replace(message_filter, ' ')