- 緒論

如何查找視頻id
項(xiàng)目結(jié)構(gòu)

制作詞云圖
制作最近評論數(shù)條形圖與折線圖
制作每小時評論條形圖與折線圖
制作最近評論數(shù)餅圖
制作每小時評論餅圖
制作觀看時間區(qū)間評論統(tǒng)計(jì)餅圖
制作雪中悍刀行主演提及占比餅圖
制作評論內(nèi)容情感分析圖
評論的時間戳轉(zhuǎn)換為正常時間
評論內(nèi)容讀入CSV
統(tǒng)計(jì)一天各個時間段內(nèi)的評論數(shù)
統(tǒng)計(jì)最近評論數(shù)
爬取評論內(nèi)容
爬取評論時間
一.爬蟲部分
二.數(shù)據(jù)處理部分
三. 數(shù)據(jù)分析

緒論

本期是對騰訊熱播劇——雪中悍刀行的一次爬蟲與數(shù)據(jù)分析，耗時一個小時，總爬取條數(shù)1W條評論，很適合新人練手，值得注意的一點(diǎn)是評論的情緒文本分析處理，這是第一次接觸的知識。

爬蟲方面：由于騰訊的評論數(shù)據(jù)是封裝在json里面，所以只需要找到j(luò)son文件，對需要的數(shù)據(jù)進(jìn)行提取保存即可。

視頻網(wǎng)址：https://v.qq.com/x/cover/mzc0020020cyvqh.html
評論json數(shù)據(jù)網(wǎng)址：https://video.coral.qq.com/varticle/7579013546/comment/v2
注：只要替換視頻數(shù)字id的值，即可爬取其他視頻的評論

如何查找視頻id？

項(xiàng)目結(jié)構(gòu)：

一. 爬蟲部分：

1.爬取評論內(nèi)容代碼：spiders.py

import requests
import re
import random

def get_html(url, params):
    uapools = [
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14'
    ]

    thisua = random.choice(uapools)
    headers = {"User-Agent": thisua}
    r = requests.get(url, headers=headers, params=params)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    r.encoding = 'utf-8'  # 不加此句出現(xiàn)亂碼
    return r.text

def parse_page(infolist, data):
    commentpat = '"content":"(.*?)"'
    lastpat = '"last":"(.*?)"'
    commentall = re.compile(commentpat, re.S).findall(data)
    next_cid = re.compile(lastpat).findall(data)[0]
    infolist.append(commentall)
    return next_cid


def print_comment_list(infolist):
    j = 0
    for page in infolist:
        print('第' + str(j + 1) + '頁\n')
        commentall = page
        for i in range(0, len(commentall)):
            print(commentall[i] + '\n')
        j += 1


def save_to_txt(infolist, path):
    fw = open(path, 'w+', encoding='utf-8')
    j = 0
    for page in infolist:
        #fw.write('第' + str(j + 1) + '頁\n')
        commentall = page
        for i in range(0, len(commentall)):
            fw.write(commentall[i] + '\n')
        j += 1
    fw.close()


def main():
    infolist = []
    vid = '7579013546';
    cid = "0";
    page_num = 3000
    url = 'https://video.coral.qq.com/varticle/' + vid + '/comment/v2'
    #print(url)

    for i in range(page_num):
        params = {'orinum': '10', 'cursor': cid}
        html = get_html(url, params)
        cid = parse_page(infolist, html)


    print_comment_list(infolist)
    save_to_txt(infolist, 'content.txt')


main()

2.爬取評論時間代碼：sp.py

import requests
import re
import random


def get_html(url, params):
    uapools = [
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14'
    ]

    thisua = random.choice(uapools)
    headers = {"User-Agent": thisua}
    r = requests.get(url, headers=headers, params=params)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    r.encoding = 'utf-8'  # 不加此句出現(xiàn)亂碼
    return r.text


def parse_page(infolist, data):
    commentpat = '"time":"(.*?)"'
    lastpat = '"last":"(.*?)"'

    commentall = re.compile(commentpat, re.S).findall(data)
    next_cid = re.compile(lastpat).findall(data)[0]

    infolist.append(commentall)

    return next_cid



def print_comment_list(infolist):
    j = 0
    for page in infolist:
        print('第' + str(j + 1) + '頁\n')
        commentall = page
        for i in range(0, len(commentall)):
            print(commentall[i] + '\n')
        j += 1


def save_to_txt(infolist, path):
    fw = open(path, 'w+', encoding='utf-8')
    j = 0
    for page in infolist:
        #fw.write('第' + str(j + 1) + '頁\n')
        commentall = page
        for i in range(0, len(commentall)):
            fw.write(commentall[i] + '\n')
        j += 1
    fw.close()


def main():
    infolist = []
    vid = '7579013546';
    cid = "0";
    page_num =3000
    url = 'https://video.coral.qq.com/varticle/' + vid + '/comment/v2'
    #print(url)

    for i in range(page_num):
        params = {'orinum': '10', 'cursor': cid}
        html = get_html(url, params)
        cid = parse_page(infolist, html)


    print_comment_list(infolist)
    save_to_txt(infolist, 'time.txt')


main()

二.數(shù)據(jù)處理部分

1.評論的時間戳轉(zhuǎn)換為正常時間 time.py

# coding=gbk
import csv
import time

csvFile = open("data.csv",'w',newline='',encoding='utf-8')
writer = csv.writer(csvFile)
csvRow = []
#print(csvRow)
f = open("time.txt",'r',encoding='utf-8')
for line in f:
    csvRow = int(line)
    #print(csvRow)

    timeArray = time.localtime(csvRow)
    csvRow = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
    print(csvRow)
    csvRow = csvRow.split()
    writer.writerow(csvRow)

f.close()
csvFile.close()

2.評論內(nèi)容讀入csv ?CD.py

# coding=gbk
import csv
csvFile = open("content.csv",'w',newline='',encoding='utf-8')
writer = csv.writer(csvFile)
csvRow = []

f = open("content.txt",'r',encoding='utf-8')
for line in f:
    csvRow = line.split()
    writer.writerow(csvRow)

f.close()
csvFile.close()

3.統(tǒng)計(jì)一天各個時間段內(nèi)的評論數(shù) py.py

# coding=gbk
import csv

from pyecharts import options as opts
from sympy.combinatorics import Subset
from wordcloud import WordCloud

with open('../Spiders/data.csv') as csvfile:
    reader = csv.reader(csvfile)

    data1 = [str(row[1])[0:2] for row in reader]

    print(data1)
print(type(data1))


#先變成集合得到seq中的所有元素，避免重復(fù)遍歷
set_seq = set(data1)
rst = []
for item in set_seq:
    rst.append((item,data1.count(item)))  #添加元素及出現(xiàn)個數(shù)
rst.sort()
print(type(rst))
print(rst)

with open("time2.csv", "w+", newline='', encoding='utf-8') as f:
    writer = csv.writer(f, delimiter=',')
    for i in rst:                # 對于每一行的，將這一行的每個元素分別寫在對應(yīng)的列中
        writer.writerow(i)

with open('time2.csv') as csvfile:
     reader = csv.reader(csvfile)
     x = [str(row[0]) for row in reader]
     print(x)
with open('time2.csv') as csvfile:
    reader = csv.reader(csvfile)
    y1 = [float(row[1]) for row in reader]
    print(y1)

4.統(tǒng)計(jì)最近評論數(shù) py1.py

# coding=gbk
import csv

from pyecharts import options as opts
from sympy.combinatorics import Subset
from wordcloud import WordCloud

with open('../Spiders/data.csv') as csvfile:
    reader = csv.reader(csvfile)

    data1 = [str(row[0]) for row in reader]
    #print(data1)
print(type(data1))


#先變成集合得到seq中的所有元素，避免重復(fù)遍歷
set_seq = set(data1)
rst = []
for item in set_seq:
    rst.append((item,data1.count(item)))  #添加元素及出現(xiàn)個數(shù)
rst.sort()
print(type(rst))
print(rst)



with open("time1.csv", "w+", newline='', encoding='utf-8') as f:
    writer = csv.writer(f, delimiter=',')
    for i in rst:                # 對于每一行的，將這一行的每個元素分別寫在對應(yīng)的列中
        writer.writerow(i)

with open('time1.csv') as csvfile:
     reader = csv.reader(csvfile)
     x = [str(row[0]) for row in reader]
     print(x)
with open('time1.csv') as csvfile:
    reader = csv.reader(csvfile)
    y1 = [float(row[1]) for row in reader]

    print(y1)

三. 數(shù)據(jù)分析

數(shù)據(jù)分析方面：涉及到了詞云圖，條形，折線，餅圖，后三者是對評論時間與主演占比的分析，然而騰訊的評論時間是以時間戳的形式顯示，所以要進(jìn)行轉(zhuǎn)換，再去統(tǒng)計(jì)出現(xiàn)次數(shù)，最后，新加了對評論內(nèi)容的情感分析。

1.制作詞云圖

wc.py

import numpy as np
import re
import jieba
from wordcloud import WordCloud
from matplotlib import pyplot as plt
from PIL import Image

# 上面的包自己安裝，不會的就百度

f = open('content.txt', 'r', encoding='utf-8')  # 這是數(shù)據(jù)源，也就是想生成詞云的數(shù)據(jù)
txt = f.read()  # 讀取文件
f.close()  # 關(guān)閉文件，其實(shí)用with就好，但是懶得改了
# 如果是文章的話，需要用到j(luò)ieba分詞，分完之后也可以自己處理下再生成詞云
newtxt = re.sub("[A-Za-z0-9\!\%\[\]\,\。]", "", txt)
print(newtxt)
words = jieba.lcut(newtxt)

img = Image.open(r'wc.jpg')  # 想要搞得形狀
img_array = np.array(img)

# 相關(guān)配置，里面這個collocations配置可以避免重復(fù)
wordcloud = WordCloud(
    background_color="white",
    width=1080,
    height=960,
    font_path="../文悅新青年.otf",
    max_words=150,
    scale=10,#清晰度
    max_font_size=100,
    mask=img_array,
    collocations=False).generate(newtxt)

plt.imshow(wordcloud)
plt.axis('off')
plt.show()
wordcloud.to_file('wc.png')

輪廓圖：wc.jpg

詞云圖：result.png （注：這里要把英文字母過濾掉）

2.制作最近評論數(shù)條形圖 DrawBar.py

# encoding: utf-8
import csv
import pyecharts.options as opts
from pyecharts.charts import Bar
from pyecharts.globals import ThemeType


class DrawBar(object):

    """繪制柱形圖類"""
    def __init__(self):
        """創(chuàng)建柱狀圖實(shí)例，并設(shè)置寬高和風(fēng)格"""
        self.bar = Bar(init_opts=opts.InitOpts(width='1500px', height='700px', theme=ThemeType.LIGHT))

    def add_x(self):
        """為圖形添加X軸數(shù)據(jù)"""
        with open('time1.csv') as csvfile:
            reader = csv.reader(csvfile)
            x = [str(row[0]) for row in reader]
            print(x)


        self.bar.add_xaxis(
            xaxis_data=x,

        )

    def add_y(self):
        with open('time1.csv') as csvfile:
            reader = csv.reader(csvfile)
            y1 = [float(row[1]) for row in reader]

            print(y1)



        """為圖形添加Y軸數(shù)據(jù)，可添加多條"""
        self.bar.add_yaxis(  # 第一個Y軸數(shù)據(jù)
            series_name="評論數(shù)",  # Y軸數(shù)據(jù)名稱
            y_axis=y1,  # Y軸數(shù)據(jù)
            label_opts=opts.LabelOpts(is_show=True,color="black"),  # 設(shè)置標(biāo)簽
            bar_max_width='100px',  # 設(shè)置柱子最大寬度
        )


    def set_global(self):
        """設(shè)置圖形的全局屬性"""
        #self.bar(width=2000,height=1000)
        self.bar.set_global_opts(
            title_opts=opts.TitleOpts(  # 設(shè)置標(biāo)題
                title='雪中悍刀行近日評論統(tǒng)計(jì)',title_textstyle_opts=opts.TextStyleOpts(font_size=35)

            ),
            tooltip_opts=opts.TooltipOpts(  # 提示框配置項(xiàng)（鼠標(biāo)移到圖形上時顯示的東西）
                is_show=True,  # 是否顯示提示框
                trigger="axis",  # 觸發(fā)類型（axis坐標(biāo)軸觸發(fā)，鼠標(biāo)移到時會有一條垂直于X軸的實(shí)線跟隨鼠標(biāo)移動，并顯示提示信息）
                axis_pointer_type="cross"  # 指示器類型（cross將會生成兩條分別垂直于X軸和Y軸的虛線，不啟用trigger才會顯示完全）
            ),
            toolbox_opts=opts.ToolboxOpts(),  # 工具箱配置項(xiàng)(什么都不填默認(rèn)開啟所有工具)

        )

    def draw(self):
        """繪制圖形"""

        self.add_x()
        self.add_y()
        self.set_global()
        self.bar.render('../Html/DrawBar.html')  # 將圖繪制到 test.html 文件內(nèi)，可在瀏覽器打開
    def run(self):
        """執(zhí)行函數(shù)"""
        self.draw()



if __name__ == '__main__':
    app = DrawBar()

app.run()

效果圖：DrawBar.html

3.制作每小時評論條形圖?DrawBar2.py

# encoding: utf-8
# encoding: utf-8
import csv
import pyecharts.options as opts
from pyecharts.charts import Bar
from pyecharts.globals import ThemeType


class DrawBar(object):

    """繪制柱形圖類"""
    def __init__(self):
        """創(chuàng)建柱狀圖實(shí)例，并設(shè)置寬高和風(fēng)格"""
        self.bar = Bar(init_opts=opts.InitOpts(width='1500px', height='700px', theme=ThemeType.MACARONS))

    def add_x(self):
        """為圖形添加X軸數(shù)據(jù)"""
        str_name1 = '點(diǎn)'

        with open('time2.csv') as csvfile:
            reader = csv.reader(csvfile)
            x = [str(row[0] + str_name1) for row in reader]
            print(x)


        self.bar.add_xaxis(
            xaxis_data=x
        )

    def add_y(self):
        with open('time2.csv') as csvfile:
            reader = csv.reader(csvfile)
            y1 = [int(row[1]) for row in reader]

            print(y1)



        """為圖形添加Y軸數(shù)據(jù)，可添加多條"""
        self.bar.add_yaxis(  # 第一個Y軸數(shù)據(jù)
            series_name="評論數(shù)",  # Y軸數(shù)據(jù)名稱
            y_axis=y1,  # Y軸數(shù)據(jù)
            label_opts=opts.LabelOpts(is_show=False),  # 設(shè)置標(biāo)簽
            bar_max_width='50px',  # 設(shè)置柱子最大寬度

        )


    def set_global(self):
        """設(shè)置圖形的全局屬性"""
        #self.bar(width=2000,height=1000)
        self.bar.set_global_opts(
            title_opts=opts.TitleOpts(  # 設(shè)置標(biāo)題
                title='雪中悍刀行各時間段評論統(tǒng)計(jì)',title_textstyle_opts=opts.TextStyleOpts(font_size=35)

            ),
            tooltip_opts=opts.TooltipOpts(  # 提示框配置項(xiàng)（鼠標(biāo)移到圖形上時顯示的東西）
                is_show=True,  # 是否顯示提示框
                trigger="axis",  # 觸發(fā)類型（axis坐標(biāo)軸觸發(fā)，鼠標(biāo)移到時會有一條垂直于X軸的實(shí)線跟隨鼠標(biāo)移動，并顯示提示信息）
                axis_pointer_type="cross"  # 指示器類型（cross將會生成兩條分別垂直于X軸和Y軸的虛線，不啟用trigger才會顯示完全）
            ),
            toolbox_opts=opts.ToolboxOpts(),  # 工具箱配置項(xiàng)(什么都不填默認(rèn)開啟所有工具)

        )

    def draw(self):
        """繪制圖形"""

        self.add_x()
        self.add_y()
        self.set_global()
        self.bar.render('../Html/DrawBar2.html')  # 將圖繪制到 test.html 文件內(nèi)，可在瀏覽器打開
    def run(self):
        """執(zhí)行函數(shù)"""
        self.draw()

if __name__ == '__main__':
    app = DrawBar()

app.run()

效果圖：DrawBar2.html

4.制作近日評論數(shù)餅圖 ? pie_pyecharts.py

import csv
from pyecharts import options as opts
from pyecharts.charts import Pie
from random import randint
from pyecharts.globals import ThemeType
with open('time1.csv') as csvfile:
    reader = csv.reader(csvfile)
    x = [str(row[0]) for row in reader]
    print(x)
with open('time1.csv') as csvfile:
    reader = csv.reader(csvfile)
    y1 = [float(row[1]) for row in reader]
    print(y1)
num = y1
lab = x
(
    Pie(init_opts=opts.InitOpts(width='1700px',height='450px',theme=ThemeType.LIGHT))#默認(rèn)900，600
    .set_global_opts(
        title_opts=opts.TitleOpts(title="雪中悍刀行近日評論統(tǒng)計(jì)",
                                               title_textstyle_opts=opts.TextStyleOpts(font_size=27)),legend_opts=opts.LegendOpts(

            pos_top="10%", pos_left="1%",# 圖例位置調(diào)整
            ),)
    .add(series_name='',center=[280, 270], data_pair=[(j, i) for i, j in zip(num, lab)])#餅圖
   .add(series_name='',center=[845, 270],data_pair=[(j,i) for i,j in zip(num,lab)],radius=['40%','75%'])#環(huán)圖
    .add(series_name='', center=[1380, 270],data_pair=[(j, i) for i, j in zip(num, lab)], rosetype='radius')#南丁格爾圖
).render('pie_pyecharts.html')

效果圖

5.制作每小時評論餅圖 ?pie_pyecharts2.py

import csv
from pyecharts import options as opts
from pyecharts.charts import Pie
from random import randint
from pyecharts.globals import ThemeType
str_name1 = '點(diǎn)'
with open('time2.csv') as csvfile:
    reader = csv.reader(csvfile)
    x = [str(row[0]+str_name1) for row in reader]
    print(x)
with open('time2.csv') as csvfile:
    reader = csv.reader(csvfile)
    y1 = [int(row[1]) for row in reader]

    print(y1)
num = y1
lab = x
(
    Pie(init_opts=opts.InitOpts(width='1650px',height='500px',theme=ThemeType.LIGHT,))#默認(rèn)900，600
     .set_global_opts(
        title_opts=opts.TitleOpts(title="雪中悍刀行每小時評論統(tǒng)計(jì)"
                                  ,title_textstyle_opts=opts.TextStyleOpts(font_size=27)),
        legend_opts=opts.LegendOpts(

            pos_top="8%", pos_left="4%",# 圖例位置調(diào)整
            ),
    )
    .add(series_name='',center=[250, 300], data_pair=[(j, i) for i, j in zip(num, lab)])#餅圖
    .add(series_name='',center=[810, 300],data_pair=[(j,i) for i,j in zip(num,lab)],radius=['40%','75%'])#環(huán)圖
    .add(series_name='', center=[1350, 300],data_pair=[(j, i) for i, j in zip(num, lab)], rosetype='radius')#南丁格爾圖
).render('pie_pyecharts2.html')

效果圖

6.制作觀看時間區(qū)間評論統(tǒng)計(jì)餅圖 ?pie_pyecharts3.py

# coding=gbk
import csv
from pyecharts import options as opts
from pyecharts.globals import ThemeType
from sympy.combinatorics import Subset
from wordcloud import WordCloud
from pyecharts.charts import Pie
from random import randintwith open(/data.csv') as csvfile:
    reader = csv.reader(csvfile)
    data2 = [int(row[1].strip('')[0:2]) for row in reader]
    #print(data2)
print(type(data2))
#先變成集合得到seq中的所有元素，避免重復(fù)遍歷
set_seq = set(data2)
list = []
for item in set_seq:
    list.append((item,data2.count(item)))  #添加元素及出現(xiàn)個數(shù)
list.sort()
print(type(list))
#print(list)
with open("time2.csv", "w+", newline='', encoding='utf-8') as f:
    writer = csv.writer(f, delimiter=',')
    for i in list:                # 對于每一行的，將這一行的每個元素分別寫在對應(yīng)的列中
        writer.writerow(i)
n = 4 #分成n組
m = int(len(list)/n)
list2 = []
for i in range(0, len(list), m):
    list2.append(list[i:i+m])

print("凌晨 : ",list2[0])
print("上午 : ",list2[1])
print("下午 : ",list2[2])
print("晚上 : ",list2[3])

with open('time2.csv') as csvfile:
    reader = csv.reader(csvfile)
    y1 = [int(row[1]) for row in reader]

    print(y1)

n =6
groups = [y1[i:i + n] for i in range(0, len(y1), n)]

print(groups)

x=['凌晨','上午','下午','晚上']
y1=[]
for y1 in groups:
    num_sum = 0
    for groups in y1:
        num_sum += groups
str_name1 = '點(diǎn)'
num = y1
lab = x
(
    Pie(init_opts=opts.InitOpts(width='1500px',height='450px',theme=ThemeType.LIGHT))#默認(rèn)900，600
        .set_global_opts(
        title_opts=opts.TitleOpts(title="雪中悍刀行觀看時間區(qū)間評論統(tǒng)計(jì)"
                                  , title_textstyle_opts=opts.TextStyleOpts(font_size=30)),
        legend_opts=opts.LegendOpts(

            pos_top="8%",  # 圖例位置調(diào)整
        ),
    )
    .add(series_name='',center=[260, 270], data_pair=[(j, i) for i, j in zip(num, lab)])#餅圖
   .add(series_name='',center=[1230, 270],data_pair=[(j,i) for i,j in zip(num,lab)],radius=['40%','75%'])#環(huán)圖
    .add(series_name='', center=[750, 270],data_pair=[(j, i) for i, j in zip(num, lab)], rosetype='radius')#南丁格爾圖
).render('pie_pyecharts3.html')

效果圖

7.制作雪中悍刀行主演提及占比餅圖 ?pie_pyecharts4.py

import csv
from pyecharts import options as opts
from pyecharts.charts import Pie
from random import randint
from pyecharts.globals import ThemeType
f = open('content.txt', 'r', encoding='utf-8')  # 這是數(shù)據(jù)源，也就是想生成詞云的數(shù)據(jù)
words = f.read()  # 讀取文件
f.close()  # 關(guān)閉文件，其實(shí)用with就好，但是懶得改了

name=["張若昀","李庚希","胡軍"]

print(name)
count=[float(words.count("張若昀")),
      float(words.count("李庚希")),
      float(words.count("胡軍"))]
print(count)
num = count
lab = name
(
    Pie(init_opts=opts.InitOpts(width='1650px',height='450px',theme=ThemeType.LIGHT))#默認(rèn)900，600
    .set_global_opts(
        title_opts=opts.TitleOpts(title="雪中悍刀行主演提及占比",
                                               title_textstyle_opts=opts.TextStyleOpts(font_size=27)),legend_opts=opts.LegendOpts(
            pos_top="3%", pos_left="33%",# 圖例位置調(diào)整
            ),)
    .add(series_name='',center=[280, 270], data_pair=[(j, i) for i, j in zip(num, lab)])#餅圖
   .add(series_name='',center=[800, 270],data_pair=[(j,i) for i,j in zip(num,lab)],radius=['40%','75%'])#環(huán)圖
    .add(series_name='', center=[1300, 270],data_pair=[(j, i) for i, j in zip(num, lab)], rosetype='radius')#南丁格爾圖
).render('pie_pyecharts4.html')

效果圖

8.評論內(nèi)容情感分析 ?SnowNLP.py

import numpy as np
from snownlp import SnowNLP
import matplotlib.pyplot as plt

f = open('content.txt', 'r', encoding='UTF-8')
list = f.readlines()
sentimentslist = []
for i in list:
    s = SnowNLP(i)

    print(s.sentiments)
    sentimentslist.append(s.sentiments)
plt.hist(sentimentslist, bins=np.arange(0, 1, 0.01), facecolor='g')
plt.xlabel('Sentiments Probability')
plt.ylabel('Quantity')
plt.title('Analysis of Sentiments')
plt.show()

效果圖（情感各分?jǐn)?shù)段出現(xiàn)頻率）?

SnowNLP情感分析是基于情感詞典實(shí)現(xiàn)的，其簡單的將文本分為兩類，積極和消極，返回值為情緒的概率，也就是情感評分在[0,1]之間，越接近1，情感表現(xiàn)越積極，越接近0，情感表現(xiàn)越消極。

福利來啦，12月的中獎名單

我們每個月都會送書，累計(jì)快有300本了。常來留言，混臉熟的就有機(jī)會上榜！恭喜下面幾位同學(xué)成功上榜！麻煩后臺輸入：「小助手」找他快遞書籍。




推薦閱讀:
入門:?最全的零基礎(chǔ)學(xué)Python的問題? |?零基礎(chǔ)學(xué)了8個月的Python??|?實(shí)戰(zhàn)項(xiàng)目?|學(xué)Python就是這條捷徑

干貨:爬取豆瓣短評，電影《后來的我們》?|?38年NBA最佳球員分析?|? ?從萬眾期待到口碑撲街！唐探3令人失望? |?笑看新倚天屠龍記?|?燈謎答題王?｜用Python做個海量小姐姐素描圖?｜碟中諜這么火，我用機(jī)器學(xué)習(xí)做個迷你推薦系統(tǒng)電影

趣味:彈球游戲? |?九宮格? |?漂亮的花?|?兩百行Python《天天酷跑》游戲!

AI:?會做詩的機(jī)器人?|?給圖片上色?|?預(yù)測收入?|?碟中諜這么火，我用機(jī)器學(xué)習(xí)做個迷你推薦系統(tǒng)電影

小工具:?Pdf轉(zhuǎn)Word，輕松搞定表格和水印！?|?一鍵把html網(wǎng)頁保存為pdf！|??再見PDF提取收費(fèi)！?|?用90行代碼打造最強(qiáng)PDF轉(zhuǎn)換器，word、PPT、excel、markdown、html一鍵轉(zhuǎn)換?|?制作一款釘釘?shù)蛢r(jià)機(jī)票提示器！?｜60行代碼做了一個語音壁紙切換器天天看小姐姐！｜

年度爆款文案
1).臥槽！Pdf轉(zhuǎn)Word用Python輕松搞定！
2).學(xué)Python真香！我用100行代碼做了個網(wǎng)站，幫人PS旅行圖片，賺個雞腿吃
3).首播過億，火爆全網(wǎng)，我分析了《乘風(fēng)破浪的姐姐》，發(fā)現(xiàn)了這些秘密?
4).80行代碼！用Python做一個哆來A夢分身?
5).你必須掌握的20個python代碼，短小精悍，用處無窮?
6).30個Python奇淫技巧集?
7).我總結(jié)的80頁《菜鳥學(xué)Python精選干貨.pdf》,都是干貨?
8).再見Python！我要學(xué)Go了！2500字深度分析！
9).發(fā)現(xiàn)一個舔狗福利！這個Python爬蟲神器太爽了，自動下載妹子圖片

點(diǎn)閱讀原文，看200個Python案例！

用Python爬取了《雪中悍刀行》數(shù)據(jù)，并將其可視化分析后，終于知道它為什么這么火了~文末送書！

緒論

如何查找視頻id？