Python数据可视化：平凡的世界

import os
import time
import requests
from bs4 import BeautifulSoup

# 初始时间
starttime = time.time()
print(starttime)
# 新建文件夹
folder_path = "F:/Python/Ordinary_world_1/"
os.makedirs(folder_path)
# 遍历
a = ['yi', 'er', 'san']
for i in a:
    for j in range(1, 55):
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
        url = 'http://www.pingfandeshijie.net/di-' + i + '-bu-' + str('%02d' % j) + '.html'
        response = requests.get(url=url, headers=headers)
        # 设置编码格式
        response.encoding = 'utf-8'
        soup = BeautifulSoup(response.text, 'lxml')
        # 获取章节情况
        h1 = soup.find('h1')
        print(h1.get_text())
        # 获取段落内容
        p = soup.find_all('p')
        for k in p:
            if '下一章' in k.get_text():
                break
            content = k.get_text().replace('S*锓', '')
            filename = h1.get_text() + '.txt'
            with open('F:\Python\Ordinary_world_1\' + filename, 'a+') as f:
                try:
                    f.write(content + '
')
                except:
                    pass
            f.close()
# 结束时间
endtime = time.time()
print(endtime)
# 程序运行总时间
print(round(endtime-starttime, 2))

import os
import time
import requests
import threading
from bs4 import BeautifulSoup

# 初始时间
starttime = time.time()
# 新建文件夹
folder_path = "F:/Python/Ordinary_world"
os.makedirs(folder_path)


def download(sta, end):
    a = ['yi', 'er', 'san']
    for i in a:
        for j in range(sta, end):
            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
            url = 'http://www.pingfandeshijie.net/di-' + i + '-bu-' + str('%02d' % j) + '.html'
            response = requests.get(url=url, headers=headers)
            # 设置编码格式
            response.encoding = 'utf-8'
            soup = BeautifulSoup(response.text, 'lxml')
            # 获取章节情况
            h1 = soup.find('h1')
            print(h1.get_text())
            # 获取段落内容
            p = soup.find_all('p')
            for k in p:
                if '下一章' in k.get_text():
                    break
                content = k.get_text()
                filename = h1.get_text() + '.txt'
                with open('F:\Python\Ordinary_world\' + filename, 'a+') as f:
                    f.write(content + '
')
                f.close()


downloadThreads = []
for chap in range(1, 55, 6):
    downloadThread = threading.Thread(target=download, args=(chap, chap+6))
    downloadThreads.append(downloadThread)
    downloadThread.start()
# 等待所有线程结束
for downloadThread in downloadThreads:
    downloadThread.join()
print('Down')
# 结束时间
endtime = time.time()
# 程序运行总时间
print(round(starttime-endtime, 2))

import re
import requests
from bs4 import BeautifulSoup

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
url = 'http://www.360doc.com/content/15/0408/11/22483181_461495582.shtml'
response = requests.get(url=url, headers=headers)
response.encoding = 'utf-8'
soup = BeautifulSoup(response.text, 'lxml')
p = soup.find_all('p')
for i in p[7:-9]:
    if '：' in i.get_text():
        result = re.findall('、(.*?)：', i.get_text())
        name = result[0].replace('二队队长', '').replace('“神汉”', '').replace('地主', '').strip()
        with open('name.txt', 'a+') as f:
            f.write(name + '
')
        f.close()

import os
# 汇总文本信息
for i in os.listdir('F:\Python\Ordinary_world_1'):
    worldFile = open('F:\Python\Ordinary_world_1\' + i)
    worldContent = worldFile.readlines()
    for j in worldContent:
        with open('world1.txt', 'a+') as f:
            f.write(j)
        f.close()
# 打开文件
file_text = open('world1.txt')
file_name = open('name.txt')
# 人物信息
names = []
for name in file_name:
    names.append(name.replace('
', ''))
# 文本信息
content = []
for line in file_text:
    content.append(line)
# 人物出现频数
data = []
for name in names:
    num = 0
    for line in content:
        if name in line:
            num += 1
        else:
            continue
    data.append((name, num))
# 生成字典
worddict = {}
for message in sorted(data, key=lambda x: x[1], reverse=True):
    if message[1] == 0:
        pass
    else:
        worddict[message[0]] = message[1]
print(worddict)

class wordcloud.WordCloud(
        font_path=None, 
        width=400, 
        height=200, 
        margin=2, 
        ranks_only=None, 
        prefer_horizontal=0.9,
        mask=None, scale=1, 
        color_func=None, 
        max_words=200, 
        min_font_size=4, 
        stopwords=None, 
        random_state=None,
        background_color='black', 
        max_font_size=None, 
        font_step=1, 
        mode='RGB', 
        relative_scaling=0.5, 
        regexp=None, 
        collocations=True,
        colormap=None, 
        normalize_plurals=True)

##参数含义如下：
font_path : string //字体路径，需要展现什么字体就把该字体路径+后缀名写上，如：font_path = '黑体.ttf'
width : int (default=400) //输出的画布宽度，默认为400像素
height : int (default=200) //输出的画布高度，默认为200像素
prefer_horizontal : float (default=0.90) //词语水平方向排版出现的频率，默认 0.9 （所以词语垂直方向排版出现频率为 0.1 ）
mask : nd-array or None (default=None) //如果参数为空，则使用二维遮罩绘制词云。如果 mask 非空，设置的宽高值将被忽略，遮罩形状被 mask 取代。除全白（#FFFFFF）的部分将不会绘制，其余部分会用于绘制词云。
scale : float (default=1) //按照比例进行放大画布，如设置为1.5，则长和宽都是原来画布的1.5倍。
min_font_size : int (default=4) //显示的最小的字体大小
font_step : int (default=1) //字体步长，如果步长大于1，会加快运算但是可能导致结果出现较大的误差。
max_words : number (default=200) //要显示的词的最大个数
stopwords : set of strings or None //设置需要屏蔽的词，如果为空，则使用内置的STOPWORDS
background_color : color value (default=”black”) //背景颜色，如background_color='white',背景颜色为白色。
max_font_size : int or None (default=None) //显示的最大的字体大小
mode : string (default=”RGB”) //当参数为“RGBA”并且background_color不为空时，背景为透明。
relative_scaling : float (default=.5) //词频和字体大小的关联性
color_func : callable, default=None //生成新颜色的函数，如果为空，则使用 self.color_func
regexp : string or None (optional) //使用正则表达式分隔输入的文本
collocations : bool, default=True //是否包括两个词的搭配

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np
import random


# 设置文本随机颜色
def random_color_func(word=None, font_size=None, position=None, orientation=None, font_path=None, random_state=None):
    h, s, l = random.choice([(188, 72, 53), (253, 63, 56), (12, 78, 69)])
    return "hsl({}, {}%, {}%)".format(h, s, l)


# 绘制圆形
x, y = np.ogrid[:1500,:1500]
mask = (x - 700) ** 2 + (y - 700) ** 2 > 700 ** 2
mask = 255 * mask.astype(int)

wc = WordCloud(
    background_color='white',
    mask=mask,
    font_path='C:WindowsFonts华康俪金黑W8.TTF',
    max_words=2000,
    max_font_size=250,
    min_font_size=15,
    color_func=random_color_func,
    prefer_horizontal=1,
    random_state=50
)

wc.generate_from_frequencies({'田海民': 76, '马来花': 15, '雷区长': 7, '胡得禄': 9, '金富': 60, '孙玉亭': 268, '田润生': 40, '田晓霞': 113, '田福堂': 460, '马国雄': 27, '张有智': 112, '黑白': 15, '周文龙': 35, '南洋女人': 12, '卫红': 32, '田福军': 346, '冯世宽': 83, '田润叶': 45, '孙少平': 431, '侯玉英': 49, '王满银': 134, '田四': 14, '金俊山': 128, '李登云': 95, '金俊武': 206, '石钟': 13, '萝卜花': 12, '惠英': 86, '高步杰': 6, '金光辉': 7, '刘根民': 50, '徐治功': 138, '徐爱云': 19, '武得全': 2, '曹书记': 38, '武宏全': 3, '孙少安': 385, '王彩娥': 42, '杨高虎': 19, '武惠良': 62, '王世才': 39, '田晓晨': 1, '刘志祥': 29, '苗凯': 82, '藏族姑娘': 14, '金俊斌': 18, '徐国强': 77, '胡永州': 17, '憨牛': 5, '高凤阁': 26, '张生民': 26, '白元': 11, '孙兰香': 12, '杜丽丽': 21, '秦富功': 12, '贾冰': 43, '金俊海': 37, '金波': 235, '金秀': 71, '胡得福': 12, '顾尔纯': 2, '金光亮': 91, '贺耀宗': 9, '白明川': 63, '古风铃': 32, '乔伯年': 65, '刘玉升': 71, '小翠': 8, '金强': 64, '胡永合': 53, '安锁子': 54, '金先生': 17, '田五': 49, '杜正贤': 13, '孙玉厚': 197})
plt.imshow(wc)
plt.axis('off')
wc.to_file("平凡的世界.jpg")
print('生成词云成功!')