# !/usr/bin/env python
# -*- coding: utf-8 -*-
__author__ = 'LiGoHi'import warnings
warnings.filterwarnings("ignore")
import jieba    #分词包
import numpy    #numpy计算包
import codecs   #codecs提供的open方法来指定打开的文件的语言编码，它会在读取的时候自动转换为内部unicode
import re
import pandas as pd
import matplotlib.pyplot as plt
from urllib import request
from bs4 import BeautifulSoup as bs
# %matplotlib inline
# from scipy.misc import imreadimport matplotlib
matplotlib.rcParams['figure.figsize'] = (10.0, 5.0)
from wordcloud import WordCloud#词云包#分析网页函数
def getNowPlayingMovie_list():  resp = request.urlopen('https://movie.douban.com/nowplaying/hangzhou/')        html_data = resp.read().decode('utf-8')    soup = bs(html_data, 'html.parser')    nowplaying_movie = soup.find_all('div', id='nowplaying')        nowplaying_movie_list = nowplaying_movie[0].find_all('li', class_='list-item')    nowplaying_list = []    for item in nowplaying_movie_list:        nowplaying_dict = {}        nowplaying_dict['id'] = item['data-subject']      for tag_img_item in item.find_all('img'):            nowplaying_dict['name'] = tag_img_item['alt']            nowplaying_list.append(nowplaying_dict)    return nowplaying_list#爬取评论函数
def getCommentsById(movieId, pageNum):eachCommentList = [];if pageNum>0:start = (pageNum-1) * 20else:return Falserequrl = 'https://movie.douban.com/subject/' + movieId + '/comments' +'?' +'start=' + str(start) + '&limit=20'print(requrl)resp = request.urlopen(requrl)html_data = resp.read().decode('utf-8')soup = bs(html_data, 'html.parser')comment_div_lits = soup.find_all('div', class_='comment')for item in comment_div_lits:if item.find_all('p')[0].string is not None:    eachCommentList.append(item.find_all('p')[0].string)return eachCommentListdef main():#循环获取第一个电影的前10页评论commentList = []NowPlayingMovie_list = getNowPlayingMovie_list()for i in range(10):    num = i + 1commentList_temp = getCommentsById(NowPlayingMovie_list[0]['id'], num)commentList.append(commentList_temp)#将列表中的数据转换为字符串comments = ''for k in range(len(commentList)):comments = comments + (str(commentList[k])).strip()#使用正则表达式去除标点符号pattern = re.compile(r'[\u4e00-\u9fa5]+')filterdata = re.findall(pattern, comments)cleaned_comments = ''.join(filterdata)#使用结巴分词进行中文分词segment = jieba.lcut(cleaned_comments)words_df=pd.DataFrame({'segment':segment})#去掉停用词stopwords=pd.read_csv("stopwords.txt",index_col=False,quoting=3,sep="\t",names=['stopword'], encoding='utf-8')#quoting=3全不引用words_df=words_df[~words_df.segment.isin(stopwords.stopword)]#统计词频words_stat=words_df.groupby(by=['segment'])['segment'].agg({"计数":numpy.size})words_stat=words_stat.reset_index().sort_values(by=["计数"],ascending=False)# 设置背景图片# alice_coloring = imread("相片.png")#用词云进行显示wordcloud=WordCloud(font_path="simhei.ttf",background_color="white",max_font_size=80)word_frequence = {x[0]:x[1] for x in words_stat.head(1000).values}# word_frequence_list = []# for key in word_frequence:#     temp = (key,word_frequence[key])#     word_frequence_list.append(temp)#     word_frequence_list = word_frequence_list# print(word_frequence_list)
wordcloud = wordcloud.fit_words(word_frequence)plt.imshow(wordcloud)plt.axis("off")plt.show()# fielname = "影评词云图.jpg"# with open(fielname,'wt') as f:#     f.save(img)#主函数
main()