for names in soup.select('dl'):      name = names.select('a')[0]['href']addname = "http://www.80dyy.cc{}".format(name)        

import re
from bs4 import BeautifulSoup
from datetime import datetime
import pandas
import sqlite3def getdetail(url):resd = requests.get(url)resd.encoding='gbk'   soupd=BeautifulSoup(resd.text,'html.parser')namels={}#print(url)for names in soupd.select('.mtext'):namels['标题'] = names.select('li')[0].contents[0].textnamels['链接']= urlaction= names.select('li')[1].textaction = action.replace('\xa0',' ')namels["演员"] = action[3:len(action)+1]return(namels)def onepage(pageurl):res = requests.get(pageurl)res.encoding = 'gbk'soup = BeautifulSoup(res.text,'html.parser')namels = []for names in soup.select('dl'):      name = names.select('a')[0]['href']#print(name)addname = "http://www.80dyy.cc{}".format(name)
        namels.append(getdetail(addname)) #break  #这个用来停止循环，等一页的所有信息都完成后删去即可return namelsnewst= []
zurl = 'http://www.80dyy.cc/80kehuan/'
resd = requests.get(zurl)
resd.encoding='gbk'
soup=BeautifulSoup(resd.text,'html.parser')
newst.extend(onepage(zurl))for i in range(2,4):listurl='http://www.80dyy.cc/80kehuan/index{}.html'.format(i)newst.extend(onepage(listurl))#print(newst)

df = pandas.DataFrame(newst)
with sqlite3.connect("dyactiondb10.sqlite") as db:df.to_sql('dyactiondb108',con = db)

df = pandas.DataFrame(newst)
df.to_excel('dyaction.xlsx')

df = pandas.DataFrame(newst)
print(df["演员"])

df = pandas.DataFrame(newst)
#print(df["演员"])
straction = " ".join(df["演员"])
print(straction)

import jiebatxt = open("ac1.txt","r",encoding='utf-8').read()ls = []
words = jieba.lcut(txt)
counts = {}
for word in words:ls.append(word)if len(word) == 1:continueelse:counts[word] = counts.get(word,0)+1items = list(counts.items())
items.sort(key = lambda x:x[1], reverse = True)
for i in range(50):word , count = items[i]print ("{:<10}{:>5}".format(word,count))

import jieba
import WordCloud
import matplotlib.pyplot as plttxt = open("ac1.txt","r",encoding='utf-8').read()wordlist = jieba.cut(text,cut_all=True)
wl_split = "/".join(wordlist)mywc = WordCloud().generate(text)
plt.imshow(mywc)
plt.axis("off")
plt.show()