python 从下载的facebook数据副本中的wall.htm中提取所有状态更新

Posted 2021-05-09

import codecs
import sys

from bs4 import BeautifulSoup


wall_file = open(sys.argv[1], "r")
wall = BeautifulSoup(wall_file, 'html.parser')
comment_divs = wall.find_all(class_="comment")
comments = [div.string for div in comment_divs]
out_file = codecs.open(sys.argv[2], "w", "utf-8")
for comment in comments:
    out_file.write("%s\n#######\n" % comment)