Last active
September 19, 2018 09:02
Use iTunes and iTools to extract Wechat chat history
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding:utf-8 -*- | |
import os | |
import re | |
import jieba.analyse | |
import matplotlib.pyplot as plt | |
from wordcloud import WordCloud | |
__author__ = 'wittyfilter' | |
data = [] | |
jieba.analyse.set_stop_words("stopwords.txt") | |
pattern = re.compile(r'\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2}|接收|发送|未知类型|网页消息|系统通知|文字|表情|图片|视频|我|[??]|、|[!!]|。') | |
# Replace xxx with your chat history file | |
with open("xxx.txt") as f: | |
mytext = f.readlines() | |
for line in mytext: | |
line = re.sub(pattern, '', line) | |
data.extend(jieba.analyse.extract_tags(line, topK=20)) | |
data = " ".join(data) | |
wordcloud = WordCloud(width=640, | |
height=480, | |
collocations=False, | |
font_path='Songti', | |
background_color='white', | |
).generate(data) | |
# Replace xxx with your own name | |
plt.title('xxx') | |
plt.imshow(wordcloud, interpolation="bilinear") | |
plt.axis('off') | |
plt.savefig('xxx.jpg', dpi=1600) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment