爬虫的使用（文字）+词频统计+词云

https://www.doutula.com/

http://www.xiaohuar.com/

http://www.budejie.com/

https://stock.tuchong.com/

https://www.y3600.cc/

http://www.haha56.net/xiaohua/gushi/

https://www.163.com/

以上网址自选两个，选择其中一个网址爬取文字并做词频和词云分析，选择另一个网址爬取图片内容。

import requests
import re
import jieba
import wordcloud
from imageio import imread

request = requests.get('http://www.haha56.net/xiaohua/gushi/')
request.encoding='gb2312'
data = request.text
link = re.findall('<a href="(.*?.html)" target="_blank">',data)
for i in link:
    if i == 'http://www.haha56.net/a/2016/01/12159.html':
        link_res = requests.get(i)
        link_res.encoding='gb2312'
        link_content = link_res.text
        link_joke1 = re.findall('【1】(.*?)&nbsp;</div>',link_content)
        for j in range(len(link_joke1)):
            link_joke1[j]=link_joke1[j].replace('&ldquo;','')
            link_joke1[j] = link_joke1[j].replace('&rdquo;', '')

    elif i == 'http://www.haha56.net/a/2016/12/14140.html':
        link_res = requests.get(i)
        link_res.encoding = 'gb2312'
        link_content = link_res.text
        link_joke2 = re.findall('''<div>
(.*?)&nbsp;</div>
<div>''', link_content)
        for j in range(len(link_joke2)):
            link_joke2[j]=link_joke2[j].replace('&mdash;','')
            link_joke2[j] = link_joke2[j].replace('u3000u3000', '')
            link_joke2[j] = link_joke2[j].replace('&ldquo;', '')
            link_joke2[j] = link_joke2[j].replace('&rdquo;', '')
            link_joke1.extend(link_joke2)

#词频统计
strjoke = str(link_joke1)


joke = jieba.lcut(strjoke)
wordcount = {}
for i in joke:
    if i in [' ',',','。',"'",'：',"?",'，',"!"]:
        continue
    if i in wordcount :
        wordcount[i] += 1
    else:
        wordcount[i] =1
list = list(wordcount.items())
def fun(i):
    return i[1]
list.sort(key=fun,reverse=True)
for j in list[:10]:
    print(f'{j[0]: >5} {j[1]:>5}')

#txt
f = open(r'C:UserscgcPycharmProjectsuntitledcgcduanzi.txt', 'w', encoding='utf8')
f.write(strjoke)
f.close()

#词云
f = open(r'C:UserscgcPycharmProjectsuntitledcgcduanzi.txt', 'r', encoding='utf8')
mask = imread(r"C:UserscgcPycharmProjectsuntitledcgc	img.png")
data = f.read()
w = wordcloud.WordCloud(font_path=r'C:WindowsFontssimkai.ttf', mask=mask, width=1000, height=700,
                        background_color="black")
w.generate(data)
w.to_file('duanzi.png')

效果图：