python小白的爬虫之旅

1、爬www.haha56.net/main/youmo网站的内容

ieimport requests
import re
response=requests.get("http://www.haha56.net/main/youmo/")
response.encoding="gb2312"
data=response.text
#print(data)
content_res = re.findall('<dd class="preview">(.*?)</dd>', data)
title_res = re.findall('<a href=".*?" target="_blank">(.*?)</a>', data)
title_res=title_res[1:11]
content_res = content_res[1:11]
for i in range(len(content_res)):
        print(title_res[i])
        print(content_res[i])

2、爬https://www.doutula.com/photo/list/网站的图片

import requests
import re
response=requests.get('https://www.doutula.com/photo/list/')
data=response.text
img_res=re.findall('data-original="(.*?)"',data)
for i in img_res:
    img_respone=requests.get(i)
    img_data=img_respone.content
    img_name=i.split('/')[-1]
    f=open(img_name,'wb')
    f.write(img_data)

3、对www.haha56.net/main/youmo网站的内容进行词频分析

import jieba
f=open(r'E:\实习\编程\实习\day07\2.txt','r',encoding='gb2312')
data=f.read()
data_jieba=jieba.lcut(data)
dict={}
for word in data_jieba:
   if len(word)==1:
       continue
   if word in{"一二","货在","一家","猛吃","时说","没带","一顿"}:
       continue
   if word in dict:
       dict[word]+=1
   else:
       dict[word]=1
def func(i):
    return i[1]
data_list=list(dict.items())
data_list.sort(key=func)
for i in data_list[0:10]:
    print(f'{i[0]:^6}{i[1]^5}')

4、对www.haha56.net/main/youmo网站的内容进行词云制作

# coding=gbk
import wordcloud
from imageio import imread
mask=imread(r'E:\实习\编程\实习\day07\3.png')
f=open(r'E:\实习\编程\实习\day07\2.txt')
data=f.read()
w=wordcloud.WordCloud(font_path=r'C:\Windows\Fonts\simfang',mask=mask,width=700,height=700,background_color="black")
w.generate(data)
w.to_file('outfile.png')