作业缘由：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3159

爬虫对象：权利的游戏

爬虫网址：https://movie.douban.com/subject/3016187/

为了防止爬取过程中ip被禁，我们需要设置一定的爬取间隔：

  • import time
  • time.sleep(5)

另外，还需要使用合理的user-agent模拟真实的浏览器去提取内容：

headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    }

 

# -*-coding:utf-8-*-
import urllib.request
from bs4 import BeautifulSoup


def getHtml(url):
    """获取url页面"""
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}
    req = urllib.request.Request(url,headers=headers)
    req = urllib.request.urlopen(req)
    content = req.read().decode('utf-8')

    return content


def getComment(url):
    """解析HTML页面"""
    html = getHtml(url)
    soupComment = BeautifulSoup(html, 'html.parser')

    comments = soupComment.findAll('span', 'short')
    onePageComments = []
    for comment in comments:
        # print(comment.getText()+'\n')
        onePageComments.append(comment.getText()+'\n')

    return onePageComments


if __name__ == '__main__':
    f = open('权利的游戏page10.txt', 'w', encoding='utf-8')
    for page in range(10):  # 豆瓣爬取多页评论需要验证。
        url = 'https://movie.douban.com/subject/3016187/comments?start=' + str(20*page) + '&limit=20&sort=new_score&status=P'
        print('第%s页的评论:' % (page+1))
        print(url + '\n')

        for i in getComment(url):
            f.write(i)
            print(i)
        print('\n')

获取词云

#-*-coding:utf-8-*-

import matplotlib.pyplot as plt
from wordcloud import WordCloud
from scipy.misc import imread
import jieba

text = open("权利的游戏page10.txt","rb").read()
#结巴分词
wordlist = jieba.cut(text,cut_all=True)
wl = " ".join(wordlist)
#print(wl)#输出分词之后的txt


#把分词后的txt写入文本文件
#fenciTxt  = open("fenciHou.txt","w+")
#fenciTxt.writelines(wl)
#fenciTxt.close()


#设置词云
wc = WordCloud(background_color = "white", #设置背景颜色
               mask = imread('quan.jpg'),  #设置背景图片
               max_words = 2000, #设置最大显示的字数
               stopwords = ["的", "这种", "这样", "还是", "就是", "这个"], #设置停用词
               font_path = "C:\Windows\Fonts\simkai.ttf",  # 设置为楷体 常规
        #设置中文字体，使得词云可以显示（词云默认字体是“DroidSansMono.ttf字体库”，不支持中文）
               max_font_size = 60,  #设置字体最大值
               random_state = 30, #设置有多少种随机生成状态，即有多少种配色方案
    )
myword = wc.generate(wl)#生成词云
wc.to_file('result.jpg')