import?urllib.request
import?requests
import?matplotlib.pyplot?as?plt
from?bs4?import?BeautifulSoup
def?readhtml（url）:#url轉(zhuǎn)換為html格式
????head={}
????data={}
????head[‘User-Agent‘]=“Mozilla/5.0?（compatible;?MSIE?8.0;?Windows?NT?6.0;?Trident/4.0;?Acoo?Browser?1.98.744;?.NET?CLR?3.5.30729）“
????req=urllib.request.Request（urldatahead）
????response=urllib.request.urlopen（req）
????html=response.read（）
????html=html.decode（‘utf-8‘）
????return?html
def?analizeimdb（htmlimdbmovieimdbrating）:#imdb的數(shù)據(jù)解析以及文件讀入
????imdb=[]
????soup=BeautifulSoup（html“html.parser“）;
????datas=soup.find_all（“tr“）;
????for?data?in?datas:
????????x=data.find_all（“td“class_=“titleColumn“）;
????????if?len（x）==0:
????????????continue;
????????blist=[];
????????for?y?in?x:
????????????blist.append（y.get_text（））;
????????imdbmovie.append（blist）;
????for?data?in?datas:
????????x=data.find_all（“td“class_=“ratingColumn?imdbRating“）;
????????if?len（x）==0:
?????????????continue;
????????blist=[];
????????for?y?in?x:
????????????blist.append（y.get_text（））;
????????imdbrating.append（blist）;
????for?i?in?range（250）:
????????x=imdbmovie[i];
????????y=imdbrating[i];
????????s=x[0]+y[0]+“\n“;
????????imdb.append（s）;
????file=open（r“C:\Users\Administrator\Desktop\3.csv““w“encoding=‘utf-8‘）;
????file.writelines（imdb）;
????file.close（）;
def?analizedou（htmldoumoviedourating）:#豆瓣的數(shù)據(jù)解析以及文件讀入
????douban=[];
????soup=BeautifulSoup（html“html.parser“）;
????datas=soup.find_all（“l(fā)i“）;
????for?data?in?datas:
????????x=data.find_all（“span“class_=“title“）;
????????if?len（x）==0:
????????????continue;
????????blist=[];
????????for?y?in?x:
????????????blist.append（y.get_text（））;
????????doumovie.append（blist）;
????for?data?in?datas:
????????x=data.find_all（“span“class_=“rating_num“）;
????????if?len（x）==0:
????????????continue;
????????blist=[];
????????for?y?in?x:
????????????blist.append（y.get_text（））;
????????dourating.append（blist）;
????for?i?in?range（250）:
????????x=doumovie[i];
????????y=dourating[i]
????????s=str（i+1）+“\t“+x[0]+‘\t‘+try_（x）+‘\t‘+y[0]+“\n“;
????????douban.append（s）;
????file=open（r“C:\Users\Administrator\Desktop\4.txt““w“encoding=‘utf-8‘）
????file.writelines（douban）;
????file.close（）;
def?try_（x）:#處理豆瓣中有些電影名稱不存在外文的情況
????try:
????????if?x[1]?in?x:
????????????return?x[1];
????except:
???????return?“??/N“;
def?douban（doumoviedourating）:???
????htmldatas=““;
????for?i?in?range（10）:
????????url=“https://movie.douban.com/top250?start=“+str（25*i）+“&filter=“;
????????html=readhtml（url）;
????????htmldatas=htmldatas