Python爬取中国票房网所有电影片名和演员名字，爬取齐鲁网大陆所有电视剧名称

爬取CBO中国票房网所有电影片名和演员名字

# -*- coding: utf-8 -*-
# 爬取CBO中国票房网所有电影片名
import json
import requests
import time

with open("moviename.txt", 'a') as fh:
    for pn in range(1,320):
        url = 'http://www.cbooo.cn/Mdata/getMdata_movie?area=50&type=0&year=0&initial=%E5%85%A8%E9%83%A8&pIndex=' + str(pn)
        print(url)
        time.sleep(2)
        try:
            result = requests.get(url).text
            jresult = json.loads(result)
            movices = jresult.get('pData')
            for movie in movices:
                moviename = movie.get('MovieName')
                print(moviename)
                fh.write(moviename + "\n")
        except:
            print('第'+ str(pn) + '失败！')

# 爬取CBO中国票房网所有演员
import json
import requests
import time

with open("moviestar.txt", 'a') as fh:
    for pn in range(1,2665):
        url = 'http://www.cbooo.cn/Mdata/getMdate_pList?area=50&type=0&year=0&initial=%E5%85%A8%E9%83%A8&pIndex=' + str(pn)
        print(url)
        time.sleep(2)
        try:
            result = requests.get(url).text
            jresult = json.loads(result)
            movices = jresult.get('pData')
            for movie in movices:
                moviename = movie.get('cnName')
                print(moviename)
                fh.write(moviename + "\n")
        except:
            print('第'+ str(pn) + '失败！')

 

爬取电视剧名称

# -*- coding: utf-8 -*-
# 爬取所有电视剧名称
# 来源：齐鲁电影网

from bs4 import BeautifulSoup
import urllib
url = "http://www.qilumovie.com/filmclass-txt/9.html"
html = urllib.request.urlopen(url).read()
htmldecode = html.decode("gbk") #重点关注
soup = BeautifulSoup(htmldecode,"lxml")
body = soup.body
maplist = body.find_all("li")

with open("tvplay.txt",'a') as fh:
    for tvl in maplist:
        tv = tvl.a.text
        print(tv)
        fh.write(tv + '\n')

 

 

如有错误，还请大侠指教一二！