作业day07

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/

http://www.haha56.net/xiaohua/gushi/ 爬取文字并做词频和词云分析

# 哈哈笑话网爬取文字
import requests
import re

response = requests.get('http://www.haha56.net/xiaohua/gushi/')
response.encoding = 'gb2312'
data = response.text

content_res = re.findall('<dd class="preview">(.*?)</dd>', data)
title_res = re.findall('<dt><a href=".*?" target="_blank">(.*?)</a></dt>', data)

for i in range(len(title_res)):
    if "<b><font color='#FF0000'>" in title_res[i]:
        title_res[i] = title_res[i].replace("<b><font color='#FF0000'>", '')
    if "</font></b>" in title_res[i]:
        title_res[i] = title_res[i].replace("</font></b>", '')
    if "\"" in title_res[i]:
        title_res[i] = title_res[i].replace("\"", '\'')
    if "<b>" in title_res[i]:
        title_res[i] = title_res[i].replace("<b>", '')
    if "</b>" in title_res[i]:
        title_res[i] = title_res[i].replace("</b>", '')
# print(title_res)
# print(content_res)


title_content_dic = {}
for i in range(len(title_res)):
    title_content_dic[title_res[i]] = content_res[i]

for i in title_content_dic.items():
    print(f'{i[0]:<40} {i[1]:<1000}')

# 哈哈笑话网词频统计
import jieba

f = open(r'F:\14\py\oldboy day03\哈哈笑话.txt', 'r', encoding='utf8')
data = f.read()
data_jieba = jieba.lcut(data)
counts = {}
excludes = {"...", "一个", "有点"}
for word in data_jieba:
    if len(word) == 1:
        continue
    else:
        rword = word
    counts[rword] = counts.get(rword, 0) + 1
for word in excludes:
    del counts[word]
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)
for i in range(10):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

# 哈哈笑话网词云
import wordcloud
from imageio import imread

mask = imread(r"F:\14\py\oldboy day03\爱心.png")

f = open(r'F:\14\py\oldboy day03\哈哈笑话.txt', 'r', encoding='utf8')
data = f.read()

w = wordcloud.WordCloud(font_path=r'C:\Windows\Fonts\simkai.ttf', mask=mask, width=200, 						height=200,background_color="white")
w.generate(data)
w.to_file('outfile1.png')

https://www.y3600.cc/ 爬取图片内容。

# 韩剧网

import requests
import re

response = requests.get('https://www.y3600.cc/')
data = response.text
# print(data)

img_url_res = re.findall('img src="(.*?)"', data)
for i in img_url_res:
    img_response = requests.get("http:" + i)
    img_data = img_response.content
    img_name = i.split('/')[-1]
    f = open(img_name + ".jpg", 'wb')
    f.write(img_data)
    f.flush()