Python爬取哆啦A梦-伴我同行2豆瓣影评并生成词云图

# 1. 导入相关库，用什么库，都写在这里
import requests
import chardet
import re

# 2. 构造请求头，这是一个反扒措施，初期学会总结，哪些网站都用了哪些，总结多了，用起来就得心应手。
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36',
    #在爬虫里面如果出现了Referer最好也粘上去，因为有时候服务器会根据Referer来判断请求时由浏览器还是爬虫发出的
    'Referer':'https://www.douban.com/'
}

# 3. 这个循环，类似于翻页操作
for i in range(0,1001,20):
    url = f"https://movie.douban.com/subject/34913671/comments?start={i}&limit=20&status=P&sort=new_score"
    # 4. 使用requests库发起请求
    response = requests.get(url,headers=headers)#发起请求得到响应
    # 5. 有时候返回结果可能会乱码，这里记得调用encoding属性，修改编码
    response.encoding = "utf-8"
    # 6. 获取返回的结果，调用的是text属性。一定要区分text和content属性的区别
    text = response.text#返回一个经过解码的字符串
    # 7. 解析数据，这里直接使用正则解析
    comments_list = [i for i in re.findall('<span class="short">(.*?)</span>',text,re.S)]
    # 8. 数据存储，针对列表中的每一条数据，我们直接使用open()函数，写入到txt文档
    for comment in comments_list:
         with open(r"哆啦A梦：伴我同行2.txt","a",encoding = "utf-8") as f :  
                    f.write(comment + "\n")

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from imageio import imread

import warnings
warnings.filterwarnings("ignore")

sentence = "湖北广水第三条街，有一条狗"

list(jieba.cut(sentence))

sentence = "湖北广水第三条街，有一条狗"

jieba.add_word("湖北广水")
jieba.add_word("有一条狗")

list(jieba.cut(sentence))

with open(r"哆啦A梦：伴我同行2.txt",encoding="utf-8") as f:
    txt = f.read()
txt = txt.split()

jieba.add_word("哆啦A梦")
jieba.add_word("大雄")

data_cut = [jieba.lcut(x) for x in txt]

# 读取停用词
with open(r"stoplist.txt",encoding="utf-8") as f:
    stop = f.read()
stop = stop.split()
# 额外添加停用词，这里我们只添加了一个空格
stop = [" "] + stop
# 去除停用词
s_data_cut = pd.Series(data_cut)
all_words_after = s_data_cut.apply(lambda x:[i for i in x if i not in stop])

all_words = []
for i in all_words_after:
    all_words.extend(i)
    
word_count = pd.Series(all_words).value_counts()

# 1、读取背景图片
back_picture = imread(r"aixin.jpg")

# 2、设置词云参数
wc = WordCloud(font_path="simhei.ttf",
               background_color="white",
               max_words=2000,
               mask=back_picture,
               max_font_size=200,
               random_state=42
              )
wc2 = wc.fit_words(word_count)

# 3、绘制词云图
plt.figure(figsize=(16,8))
plt.imshow(wc2)
plt.axis("off")
plt.show()
wc.to_file("ciyun.png")