add douban movie crawler with tkinter.py
This commit is contained in:
sqzhang
parent
f14e78a8dd
commit
5d6787b434
|
|
@ -0,0 +1,62 @@
|
|||
# 6.爬取豆瓣排行榜电影数据(含GUI界面版)
|
||||
|
||||
|
||||
## 项目简介
|
||||
|
||||
这个项目源于大三某课程设计。平常经常需要搜索一些电影，但是不知道哪些评分高且评价人数多的电影。为了方便使用，就将原来的项目重新改写了。当做是对爬虫技术、可视化技术的实践了。主要是通过从排行榜和从影片关键词两种方式爬取电影数据。
|
||||
|
||||
|
||||
|
||||
## 配置说明
|
||||
|
||||
1. 打开[http://chromedriver.storage.googleapis.com/index.html][1]，根据自己的操作系统下载对应的chromedriver
|
||||
2. 打开当前面目录下的**<u>getMovieInRankingList.py</u>**，定位到第59行，将`executable_path=/Users/bird/Desktop/chromedriver.exe`修改成你自己的chromedriver路径
|
||||
3. 打开pycharm，依次安装以下包
|
||||
- pip install Pillow
|
||||
- pip install selenium
|
||||
|
||||
|
||||
|
||||
## 功能截图
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## 包含功能
|
||||
|
||||
- [x] 根据关键字搜索电影
|
||||
- [x] 根据排行榜(TOP250)搜索电影
|
||||
- [x] 显示IMDB评分及其他基本信息
|
||||
- [x] 提供多个在线视频站点，无需vip
|
||||
- [x] 提供多个云盘站点搜索该视频，以便保存到云盘
|
||||
- [x] 提供多个站点下载该视频
|
||||
- [ ] 等待更新
|
||||
|
||||
|
||||
## 存在问题
|
||||
|
||||
目前没有加入反爬虫策略，如果运行出现403 forbidden提示，则说明暂时被禁止，解决方式如下：
|
||||
|
||||
- 加入cookies
|
||||
- 采用随机延时方式
|
||||
- 采用IP代理池方式(较不稳定)
|
||||
|
||||
|
||||
## 补充
|
||||
|
||||
项目持续更新，欢迎您[star本项目][5]
|
||||
|
||||
|
||||
|
||||
## License
|
||||
[The MIT License (MIT)][6]
|
||||
|
||||
|
||||
[1]:http://chromedriver.storage.googleapis.com/index.html
|
||||
[5]:https://github.com/shengqiangzhang/examples-of-web-crawlers
|
||||
[6]:http://opensource.org/licenses/MIT
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 348 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 333 KiB |
|
|
@ -0,0 +1,158 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
from ssl import _create_unverified_context
|
||||
from json import loads
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.chrome.options import Options
|
||||
from selenium.webdriver.common.by import By
|
||||
from selenium.webdriver.support.ui import WebDriverWait
|
||||
from selenium.webdriver.support import expected_conditions as EC
|
||||
import tkinter.messagebox
|
||||
|
||||
import urllib.request
|
||||
import urllib.parse
|
||||
|
||||
movieData = ' [' \
|
||||
'{"title":"纪录片", "type":"1", "interval_id":"100:90"}, ' \
|
||||
' {"title":"传记", "type":"2", "interval_id":"100:90"}, ' \
|
||||
' {"title":"犯罪", "type":"3", "interval_id":"100:90"}, ' \
|
||||
' {"title":"历史", "type":"4", "interval_id":"100:90"}, ' \
|
||||
' {"title":"动作", "type":"5", "interval_id":"100:90"}, ' \
|
||||
' {"title":"情色", "type":"6", "interval_id":"100:90"}, ' \
|
||||
' {"title":"歌舞", "type":"7", "interval_id":"100:90"}, ' \
|
||||
' {"title":"儿童", "type":"8", "interval_id":"100:90"}, ' \
|
||||
' {"title":"悬疑", "type":"10", "interval_id":"100:90"}, ' \
|
||||
' {"title":"剧情", "type":"11", "interval_id":"100:90"}, ' \
|
||||
' {"title":"灾难", "type":"12", "interval_id":"100:90"}, ' \
|
||||
' {"title":"爱情", "type":"13", "interval_id":"100:90"}, ' \
|
||||
' {"title":"音乐", "type":"14", "interval_id":"100:90"}, ' \
|
||||
' {"title":"冒险", "type":"15", "interval_id":"100:90"}, ' \
|
||||
' {"title":"奇幻", "type":"16", "interval_id":"100:90"}, ' \
|
||||
' {"title":"科幻", "type":"17", "interval_id":"100:90"}, ' \
|
||||
' {"title":"运动", "type":"18", "interval_id":"100:90"}, ' \
|
||||
' {"title":"惊悚", "type":"19", "interval_id":"100:90"}, ' \
|
||||
' {"title":"恐怖", "type":"20", "interval_id":"100:90"}, ' \
|
||||
' {"title":"战争", "type":"22", "interval_id":"100:90"}, ' \
|
||||
' {"title":"短片", "type":"23", "interval_id":"100:90"}, ' \
|
||||
' {"title":"喜剧", "type":"24", "interval_id":"100:90"}, ' \
|
||||
' {"title":"动画", "type":"25", "interval_id":"100:90"}, ' \
|
||||
' {"title":"同性", "type":"26", "interval_id":"100:90"}, ' \
|
||||
' {"title":"西部", "type":"27", "interval_id":"100:90"}, ' \
|
||||
' {"title":"家庭", "type":"28", "interval_id":"100:90"}, ' \
|
||||
' {"title":"武侠", "type":"29", "interval_id":"100:90"}, ' \
|
||||
' {"title":"古装", "type":"30", "interval_id":"100:90"}, ' \
|
||||
' {"title":"黑色电影", "type":"31", "interval_id":"100:90"}' \
|
||||
']'
|
||||
|
||||
|
||||
class getMovieInRankingList:
|
||||
|
||||
# typeId 电影类型, movie_count 欲获取的该电影类型的数量, rating 电影的评分, vote_count 电影的评价人数
|
||||
def __init__(self):
|
||||
chrome_options = Options()
|
||||
chrome_options.add_argument('--headless') # 设置为无头模式，即不显示浏览器
|
||||
chrome_options.add_argument(
|
||||
'user-agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"') # 设置user=agent
|
||||
chrome_options.add_experimental_option('excludeSwitches',['enable-automation']) # 此步骤很重要，设置为开发者模式，防止被各大网站识别出来使用了Selenium
|
||||
chrome_options.add_experimental_option("prefs",{"profile.managed_default_content_settings.images": 2}) # 不加载图片,加快访问速度
|
||||
|
||||
try:
|
||||
self.browser = webdriver.Chrome(executable_path='/Users/bird/Desktop/chromedriver.exe',chrome_options=chrome_options) # 设置chromedriver路径
|
||||
self.wait = WebDriverWait(self.browser, 10) # 超时时长为10s
|
||||
except:
|
||||
print("chromedriver.exe出错，请检查是否与你的chrome浏览器版本相匹配\n缺失chromedriver.exe不会导致从排行榜搜索功能失效，但会导致从关键字搜索功能失效")
|
||||
|
||||
# 从排行榜中获取电影数据
|
||||
def get_url_data_in_ranking_list(self, typeId, movie_count, rating, vote_count):
|
||||
context = _create_unverified_context() # 屏蔽ssl证书
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36', }
|
||||
url = 'https://movie.douban.com/j/chart/top_list?type=' + str(
|
||||
typeId) + '&interval_id=100:90&action=unwatched&start=0&limit=' + str(movie_count)
|
||||
req = urllib.request.Request(url=url, headers=headers)
|
||||
f = urllib.request.urlopen(req, context=context)
|
||||
response = f.read()
|
||||
jsonData = loads(response) # 将json转为python对象
|
||||
|
||||
list = []
|
||||
for subData in jsonData: # 依次对每部电影进行操作
|
||||
if ((float(subData['rating'][0]) >= float(rating)) and (float(subData['vote_count']) >= float(vote_count))):
|
||||
subList = []
|
||||
subList.append(subData['title'])
|
||||
subList.append(subData['rating'][0])
|
||||
subList.append(subData['rank'])
|
||||
subList.append(subData['vote_count'])
|
||||
list.append(subList)
|
||||
|
||||
for data in list:
|
||||
print(data)
|
||||
|
||||
return list, jsonData
|
||||
|
||||
# 从关键字获取电影数据
|
||||
def get_url_data_in_keyWord(self, key_word):
|
||||
|
||||
# 浏览网页
|
||||
self.browser.get('https://movie.douban.com/subject_search?search_text=' + urllib.parse.quote(
|
||||
key_word) + '&cat=1002') # get方式获取返回数据
|
||||
|
||||
# js动态渲染的网页,必须等到搜索结果元素(DIV中class=root)出来后，才可以停止加载网页
|
||||
# 等待DIV中class=root的元素出现
|
||||
self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.root')))
|
||||
|
||||
dr = self.browser.find_elements_by_xpath("//div[@class='item-root']") # 获取class为item-root的DIV(因为有多个结果)
|
||||
jsonData = []
|
||||
list = []
|
||||
for son in dr:
|
||||
movieData = {'rating': ['', 'null'], 'cover_url': '', 'types': '', 'title': '', 'url': '',
|
||||
'release_date': '', 'vote_count': '', 'actors': ''}
|
||||
subList = ['', '', '', '']
|
||||
|
||||
url_element = son.find_elements_by_xpath(".//a") # 获取第一个a标签的url(因为有多个结果)
|
||||
if (url_element):
|
||||
movieData['url'] = (url_element[0].get_attribute("href"))
|
||||
|
||||
img_url_element = url_element[0].find_elements_by_xpath(".//img") # 获取影片海报图片地址
|
||||
if (img_url_element):
|
||||
movieData['cover_url'] = (img_url_element[0].get_attribute("src"))
|
||||
|
||||
title_element = son.find_elements_by_xpath(".//div[@class='title']") # 获取标题
|
||||
if (title_element):
|
||||
temp_title = (title_element[0].text)
|
||||
movieData['title'] = (temp_title.split('('))[0]
|
||||
movieData['release_date'] = temp_title[temp_title.find('(') + 1:temp_title.find(')')]
|
||||
subList[0] = movieData['title']
|
||||
|
||||
rating_element = son.find_elements_by_xpath(".//span[@class='rating_nums']") # 获取评分
|
||||
if (rating_element):
|
||||
movieData['rating'][0] = (rating_element[0].text)
|
||||
subList[1] = movieData['rating'][0]
|
||||
|
||||
vote_element = son.find_elements_by_xpath(".//span[@class='pl']") # 获取数量
|
||||
if (vote_element):
|
||||
movieData['vote_count'] = (vote_element[0].text).replace('(', '').replace(')', '').replace('人评价', '')
|
||||
subList[3] = movieData['vote_count']
|
||||
|
||||
type_element = son.find_elements_by_xpath(".//div[@class='meta abstract']") # 获取类型
|
||||
if (type_element):
|
||||
movieData['types'] = (type_element[0].text)
|
||||
subList[2] = movieData['types']
|
||||
|
||||
actors_element = son.find_elements_by_xpath(".//div[@class='meta abstract_2']") # 获取演员
|
||||
if (actors_element):
|
||||
movieData['actors'] = (actors_element[0].text)
|
||||
|
||||
jsonData.append(movieData)
|
||||
list.append(subList)
|
||||
|
||||
# 关闭浏览器
|
||||
self.browser.quit()
|
||||
|
||||
for data in list:
|
||||
print(data)
|
||||
|
||||
return list, jsonData
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
|
||||
|
||||
from uiObject import uiObject
|
||||
|
||||
# main入口
|
||||
if __name__ == '__main__':
|
||||
|
||||
ui = uiObject()
|
||||
ui.ui_process()
|
||||
|
|
@ -0,0 +1,931 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
|
||||
from PIL import Image, ImageTk
|
||||
from getMovieInRankingList import *
|
||||
from tkinter import Tk
|
||||
from tkinter import ttk
|
||||
from tkinter import font
|
||||
from tkinter import LabelFrame
|
||||
from tkinter import Label
|
||||
from tkinter import StringVar
|
||||
from tkinter import Entry
|
||||
from tkinter import END
|
||||
from tkinter import Button
|
||||
from tkinter import Frame
|
||||
from tkinter import RIGHT
|
||||
from tkinter import NSEW
|
||||
from tkinter import NS
|
||||
from tkinter import NW
|
||||
from tkinter import N
|
||||
from tkinter import Y
|
||||
from tkinter import DISABLED
|
||||
from tkinter import NORMAL
|
||||
from re import findall
|
||||
from json import loads
|
||||
from threading import Thread
|
||||
from urllib.parse import quote
|
||||
from webbrowser import open
|
||||
import os
|
||||
import ssl
|
||||
ssl._create_default_https_context = ssl._create_unverified_context #关闭SSL证书验证
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def thread_it(func, *args):
|
||||
'''
|
||||
将函数打包进线程
|
||||
'''
|
||||
# 创建
|
||||
t = Thread(target=func, args=args)
|
||||
# 守护
|
||||
t.setDaemon(True)
|
||||
# 启动
|
||||
t.start()
|
||||
|
||||
|
||||
def handlerAdaptor(fun, **kwds):
|
||||
'''事件处理函数的适配器，相当于中介，那个event是从那里来的呢，我也纳闷，这也许就是python的伟大之处吧'''
|
||||
return lambda event, fun=fun, kwds=kwds: fun(event, **kwds)
|
||||
|
||||
|
||||
|
||||
def save_img(img_url, file_name, file_path):
|
||||
"""
|
||||
下载指定url的图片，并保存运行目录下的img文件夹
|
||||
:param img_url: 图片地址
|
||||
:param file_name: 图片名字
|
||||
:param file_path: 存储目录
|
||||
:return:
|
||||
"""
|
||||
#保存图片到磁盘文件夹 file_path中，默认为当前脚本运行目录下的img文件夹
|
||||
try:
|
||||
#判断文件夹是否已经存在
|
||||
if not os.path.exists(file_path):
|
||||
print('文件夹',file_path,'不存在，重新建立')
|
||||
os.makedirs(file_path)
|
||||
#获得图片后缀
|
||||
file_suffix = os.path.splitext(img_url)[1]
|
||||
#拼接图片名（包含路径）
|
||||
filename = '{}{}{}{}'.format(file_path,os.sep,file_name,file_suffix)
|
||||
|
||||
#判断文件是否已经存在
|
||||
if not os.path.exists(filename):
|
||||
print('文件', filename, '不存在，重新建立')
|
||||
# 下载图片，并保存到文件夹中
|
||||
urllib.request.urlretrieve(img_url, filename=filename)
|
||||
return filename
|
||||
|
||||
except IOError as e:
|
||||
print('下载图片操作失败',e)
|
||||
except Exception as e:
|
||||
print('错误:',e)
|
||||
|
||||
|
||||
|
||||
def resize(w_box, h_box, pil_image):
|
||||
"""
|
||||
等比例缩放图片,并且限制在指定方框内
|
||||
:param w_box,h_box: 指定方框的宽度和高度
|
||||
:param pil_image: 原始图片
|
||||
:return:
|
||||
"""
|
||||
|
||||
f1 = 1.0 * w_box / pil_image.size[0] # 1.0 forces float division in Python2
|
||||
f2 = 1.0 * h_box / pil_image.size[1]
|
||||
factor = min([f1, f2])
|
||||
# print(f1, f2, factor) # test
|
||||
# use best down-sizing filter
|
||||
width = int(pil_image.size[0] * factor)
|
||||
height = int(pil_image.size[1] * factor)
|
||||
return pil_image.resize((width, height), Image.ANTIALIAS)
|
||||
|
||||
|
||||
def get_mid_str(content,startStr,endStr):
|
||||
startIndex = content.index(startStr)
|
||||
if startIndex>=0:
|
||||
startIndex += len(startStr)
|
||||
endIndex = content.index(endStr)
|
||||
return content[startIndex:endIndex]
|
||||
|
||||
|
||||
class uiObject:
|
||||
|
||||
def __init__(self):
|
||||
self.jsonData = ""
|
||||
self.jsonData_keyword = ""
|
||||
|
||||
|
||||
def show_GUI_movie_detail(self):
|
||||
'''
|
||||
显示 影片详情 界面GUI
|
||||
'''
|
||||
self.label_img['state'] = NORMAL
|
||||
self.label_movie_name['state'] = NORMAL
|
||||
self.label_movie_rating['state'] = NORMAL
|
||||
self.label_movie_time['state'] = NORMAL
|
||||
self.label_movie_type['state'] = NORMAL
|
||||
self.label_movie_actor['state'] = NORMAL
|
||||
|
||||
|
||||
def hidden_GUI_movie_detail(self):
|
||||
'''
|
||||
显示 影片详情 界面GUI
|
||||
'''
|
||||
self.label_img['state'] = DISABLED
|
||||
self.label_movie_name['state'] = DISABLED
|
||||
self.label_movie_rating['state'] = DISABLED
|
||||
self.label_movie_time['state'] = DISABLED
|
||||
self.label_movie_type['state'] = DISABLED
|
||||
self.label_movie_actor['state'] = DISABLED
|
||||
|
||||
|
||||
|
||||
def show_IDMB_rating(self):
|
||||
'''
|
||||
显示IDM评分
|
||||
'''
|
||||
|
||||
self.label_movie_rating_imdb.config(text='正在加载IMDB评分')
|
||||
self.B_0_imdb['state'] = DISABLED
|
||||
rating_imdb = '未知'
|
||||
|
||||
|
||||
|
||||
item = self.treeview.selection()
|
||||
if(item):
|
||||
item_text = self.treeview.item(item, "values")
|
||||
movieName = item_text[0] # 输出电影名
|
||||
for movie in self.jsonData:
|
||||
if(movie['title'] == movieName):
|
||||
|
||||
f = urllib.request.urlopen(movie['url'])
|
||||
response = (f.read()).decode()
|
||||
url_imdb = get_mid_str(response, 'IMDb链接:</span> <a href=\"', '\" target=\"_blank\" rel=\"nofollow\">')
|
||||
|
||||
f = urllib.request.urlopen(url_imdb)
|
||||
data_imdb = (f.read()).decode()
|
||||
rating_imdb = get_mid_str(data_imdb, '<span class=\"rating">', '<span class=\"ofTen\">')
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
self.clear_tree(self.treeview_play_online)
|
||||
s = response
|
||||
name = findall(r"<a class=\"playBtn\" data-cn=\"(.*?)\" href=\"", s)
|
||||
down_url = findall(r"data-cn=\".*?\" href=\"(.*?)\" target=", s)
|
||||
real_movie_name = get_mid_str(s, "<title>", "</title>").replace(" ","").replace("\n","").replace("(豆瓣)","")
|
||||
print(real_movie_name)
|
||||
list = []
|
||||
for i in range(len(name)):
|
||||
list.append([name[i], "限VIP免费", down_url[i]])
|
||||
list.append(["4K屋", "免费", "http://www.4kwu.cc/?m=vod-search&wd=" + quote(real_movie_name)])
|
||||
list.append(["91黑米", "免费", "http://www.91heimi.com/index.php/vod/search.html?wd=" + quote(real_movie_name)])
|
||||
list.append(["AAQQS", "免费", "http://aaxxy.com/vod-search-pg-1-wd-" + quote(real_movie_name) + ".html"])
|
||||
list.append(["Neets", "免费", "http://neets.cc/search?key=" + quote(real_movie_name)])
|
||||
list.append(["Q2电影网", "免费", "http://www.q2002.com/search?wd=" + quote(real_movie_name)])
|
||||
list.append(["霸气村", "免费", "http://www.baqicun.co/search.php?searchword=" + quote(real_movie_name)])
|
||||
list.append(["魔力电影网", "免费", "http://www.magbt.net/search.php?searchword=" + quote(real_movie_name)])
|
||||
list.append(["新论语", "免费", "http://www.honggujiu.net/index.php?m=vod-search&wd=" + quote(real_movie_name)])
|
||||
list.append(["左手吃斋", "免费", "https://www.xiangkanju.com/index.php?m=vod-search&wd=" + quote(real_movie_name)])
|
||||
self.add_tree(list, self.treeview_play_online)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
self.clear_tree(self.treeview_save_cloud_disk)
|
||||
list = []
|
||||
list.append(["56网盘搜索", "有效", "https://www.56wangpan.com/search/o2kw" + quote(real_movie_name)])
|
||||
list.append(["爱搜资源", "有效", "https://www.aisouziyuan.com/?name=" + quote(real_movie_name) + "&page=1"])
|
||||
list.append(["盘多多", "有效", "http://www.panduoduo.net/s/comb/n-" + quote(real_movie_name) + "&f-f4"])
|
||||
list.append(["小白盘", "有效", "https://www.xiaobaipan.com/list-" + quote(real_movie_name) + "-1.html" ])
|
||||
list.append(["云盘精灵", "有效", "https://www.yunpanjingling.com/search/" + quote(real_movie_name) + "?sort=size.desc"])
|
||||
self.add_tree(list, self.treeview_save_cloud_disk)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
self.clear_tree(self.treeview_bt_download)
|
||||
list = []
|
||||
list.append( ['19影视', '有效', 'https://www.19kan.com/vodsearch.html?wd=' + quote(real_movie_name) ])
|
||||
list.append( ['2TU影院', '有效', 'http://www.82tu.cc/search.php?submit=%E6%90%9C+%E7%B4%A2&searchword=' + quote(real_movie_name) ])
|
||||
list.append( ['4K电影', '有效', 'https://www.dygc.org/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['52 Movie', '有效', 'http://www.52movieba.com/search.htm?keyword=' + quote(real_movie_name) ])
|
||||
list.append( ['592美剧', '有效', 'http://www.592meiju.com/search/?wd=' + quote(real_movie_name) ])
|
||||
list.append( ['97电影网', '有效', 'http://www.55xia.com/search?q=' + quote(real_movie_name) ])
|
||||
list.append( ['98TVS', '有效', 'http://www.98tvs.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['9去这里', '有效', 'http://9qzl.com/index.php?s=/video/search/wd/' + quote(real_movie_name) ])
|
||||
list.append( ['CK电影', '有效', 'http://www.ck180.net/search.html?q=' + quote(real_movie_name) ])
|
||||
list.append( ['LOL电影', '有效', 'http://www.993dy.com/index.php?m=vod-search&wd=' + quote(real_movie_name) ])
|
||||
list.append( ['MP4Vv', '有效', 'http://www.mp4pa.com/search.php?searchword=' + quote(real_movie_name) ])
|
||||
list.append( ['MP4电影', '有效', 'http://www.domp4.com/search/' + quote(real_movie_name) + '-1.html'])
|
||||
list.append( ['TL95', '有效', 'http://www.tl95.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['比特大雄', '有效', 'https://www.btdx8.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['比特影视', '有效', 'https://www.bteye.com/search/' + quote(real_movie_name) ])
|
||||
list.append( ['春晓影视', '有效', 'http://search.chunxiao.tv/?keyword=' + quote(real_movie_name) ])
|
||||
list.append( ['第一电影网', '有效', 'https://www.001d.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['电影日志', '有效', 'http://www.dyrizhi.com/search?s=' + quote(real_movie_name) ])
|
||||
list.append( ['高清888', '有效', 'https://www.gaoqing888.com/search?kw=' + quote(real_movie_name) ])
|
||||
list.append( ['高清MP4', '有效', 'http://www.mp4ba.com/index.php?m=vod-search&wd=' + quote(real_movie_name) ])
|
||||
list.append( ['高清电台', '有效', 'https://gaoqing.fm/s.php?q=' + quote(real_movie_name) ])
|
||||
list.append( ['高清控', '有效', 'http://www.gaoqingkong.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['界绍部', '有效', 'http://www.jsb456.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['看美剧', '有效', 'http://www.kanmeiju.net/index.php?s=/video/search/wd/' + quote(real_movie_name) ])
|
||||
list.append( ['蓝光网', '有效', 'http://www.languang.co/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['老司机电影', '有效', 'http://www.lsjdyw.net/search/?s=' + quote(real_movie_name) ])
|
||||
list.append( ["乐赏电影", '有效', 'http://www.gscq.me/search.htm?keyword=' + quote(real_movie_name) ])
|
||||
list.append( ["美剧汇", '有效', 'http://www.meijuhui.net/search.php?q=' + quote(real_movie_name) ])
|
||||
list.append( ['美剧鸟', '有效', 'http://www.meijuniao.com/index.php?s=vod-search-wd-' + quote(real_movie_name) ])
|
||||
list.append( ['迷你MP4', '有效', 'http://www.minimp4.com/search?q=' + quote(real_movie_name) ])
|
||||
list.append( ['泡饭影视', '有效', 'http://www.chapaofan.com/search/' + quote(real_movie_name) ])
|
||||
list.append( ['片吧', '有效', 'http://so.pianbar.com/search.aspx?q=' + quote(real_movie_name) ])
|
||||
list.append( ['片源网', '有效', 'http://pianyuan.net/search?q=' + quote(real_movie_name) ])
|
||||
list.append( ['飘花资源网', '有效', 'https://www.piaohua.com/plus/search.php?kwtype=0&keyword=' + quote(real_movie_name) ])
|
||||
list.append( ['趣味源', '有效', 'http://quweiyuan.cc/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['人生05', '有效', 'http://www.rs05.com/search.php?s=' + quote(real_movie_name) ])
|
||||
list.append( ['贪玩影视', '有效', 'http://www.tanwanyingshi.com/movie/search?keyword=' + quote(real_movie_name) ])
|
||||
list.append( ['新片网', '有效', 'http://www.91xinpian.com/index.php?m=vod-search&wd=' + quote(real_movie_name) ])
|
||||
list.append( ['迅雷影天堂', '有效', 'https://www.xl720.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['迅影网', '有效', 'http://www.xunyingwang.com/search?q=' + quote(real_movie_name) ])
|
||||
list.append( ['一只大榴莲', '有效', 'http://www.llduang.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['音范丝', '有效', 'http://www.yinfans.com/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['影海', '有效', 'http://www.yinghub.com/search/list.html?keyword=' + quote(real_movie_name) ])
|
||||
list.append( ['影视看看', '有效', 'http://www.yskk.tv/index.php?m=vod-search&wd=' + quote(real_movie_name) ])
|
||||
list.append( ['云播网', '有效', 'http://www.yunbowang.cn/index.php?m=vod-search&wd=' + quote(real_movie_name) ])
|
||||
list.append( ['中国高清网', '有效', 'http://gaoqing.la/?s=' + quote(real_movie_name) ])
|
||||
list.append( ['最新影视站', '有效', 'http://www.zxysz.com/?s=' + quote(real_movie_name) ])
|
||||
self.add_tree(list, self.treeview_bt_download)
|
||||
|
||||
|
||||
|
||||
break;
|
||||
|
||||
self.label_movie_rating_imdb.config(text='IMDB评分:' + rating_imdb + '分')
|
||||
|
||||
|
||||
|
||||
def project_statement_show(self, event):
|
||||
open("https://github.com/shengqiangzhang/examples-of-web-crawlers")
|
||||
|
||||
def project_statement_get_focus(self, event):
|
||||
self.project_statement.config(fg="blue", cursor="hand1")
|
||||
|
||||
def project_statement_lose_focus(self, event):
|
||||
self.project_statement.config(fg="#FF0000")
|
||||
|
||||
|
||||
def show_movie_data(self, event):
|
||||
'''
|
||||
显示某个被选择的电影的详情信息
|
||||
'''
|
||||
|
||||
# self.hidden_GUI_movie_detail()
|
||||
|
||||
self.B_0_imdb['state'] = NORMAL
|
||||
self.label_movie_rating_imdb.config(text = 'IMDB评分')
|
||||
self.clear_tree(self.treeview_play_online)
|
||||
self.clear_tree(self.treeview_save_cloud_disk)
|
||||
self.clear_tree(self.treeview_bt_download)
|
||||
|
||||
item = self.treeview.selection()
|
||||
if(item):
|
||||
item_text = self.treeview.item(item, "values")
|
||||
movieName = item_text[0] # 输出电影名
|
||||
for movie in self.jsonData:
|
||||
if(movie['title'] == movieName):
|
||||
img_url = movie['cover_url']
|
||||
movie_name = movie['title']
|
||||
file_name = save_img(img_url, movie_name, 'img') #下载网络图片
|
||||
self.show_movie_img(file_name)
|
||||
self.label_movie_name.config(text=movie['title'])
|
||||
if(isinstance(movie['actors'],list)):
|
||||
string_actors = "、".join(movie['actors'])
|
||||
else:
|
||||
string_actors = movie['actors']
|
||||
self.label_movie_actor.config(text=string_actors)
|
||||
self.label_movie_rating.config(text=str(movie['rating'][0]) + '分 ' + str(movie['vote_count']) + '人评价')
|
||||
self.label_movie_time.config(text=movie['release_date'])
|
||||
self.label_movie_type.config(text=movie['types'])
|
||||
|
||||
break
|
||||
|
||||
# self.show_GUI_movie_detail()
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def show_movie_img(self, file_name):
|
||||
'''
|
||||
更新图片GUI
|
||||
:param file_name: 图片路径
|
||||
:return:
|
||||
'''
|
||||
img_open = Image.open(file_name) #读取本地图片
|
||||
pil_image_resized = resize(160, 230, img_open) #等比例缩放本地图片
|
||||
img = ImageTk.PhotoImage(pil_image_resized) #读入图片
|
||||
self.label_img.config(image=img, width = pil_image_resized.size[0], height = pil_image_resized.size[1])
|
||||
self.label_img.image = img
|
||||
|
||||
|
||||
def center_window(self, root, w, h):
|
||||
"""
|
||||
窗口居于屏幕中央
|
||||
:param root: root
|
||||
:param w: 窗口宽度
|
||||
:param h: 窗口高度
|
||||
:return:
|
||||
"""
|
||||
# 获取屏幕 宽、高
|
||||
ws = root.winfo_screenwidth()
|
||||
hs = root.winfo_screenheight()
|
||||
|
||||
# 计算 x, y 位置
|
||||
x = (ws/2) - (w/2)
|
||||
y = (hs/2) - (h/2)
|
||||
|
||||
root.geometry('%dx%d+%d+%d' % (w, h, x, y))
|
||||
|
||||
|
||||
|
||||
def clear_tree(self, tree):
|
||||
'''
|
||||
清空表格
|
||||
'''
|
||||
x = tree.get_children()
|
||||
for item in x:
|
||||
tree.delete(item)
|
||||
|
||||
def add_tree(self,list, tree):
|
||||
'''
|
||||
新增数据到表格
|
||||
'''
|
||||
i = 0
|
||||
for subList in list:
|
||||
tree.insert('', 'end', values=subList)
|
||||
i = i + 1
|
||||
tree.grid()
|
||||
|
||||
|
||||
def searh_movie_in_rating(self):
|
||||
"""
|
||||
从排行榜中搜索符合条件的影片信息
|
||||
"""
|
||||
|
||||
# 按钮设置为灰色状态
|
||||
self.clear_tree(self.treeview) # 清空表格
|
||||
self.B_0['state'] = DISABLED
|
||||
self.C_type['state'] = DISABLED
|
||||
self.T_count['state'] = DISABLED
|
||||
self.T_rating['state'] = DISABLED
|
||||
self.T_vote['state'] = DISABLED
|
||||
self.B_0_keyword['state'] = DISABLED
|
||||
self.T_vote_keyword['state'] = DISABLED
|
||||
self.B_0['text'] = '正在努力搜索'
|
||||
self.jsonData = ""
|
||||
|
||||
|
||||
jsonMovieData = loads(movieData)
|
||||
for subMovieData in jsonMovieData:
|
||||
if(subMovieData['title'] == self.C_type.get()):
|
||||
|
||||
movieObject = getMovieInRankingList() #创建对象
|
||||
list,jsonData = movieObject.get_url_data_in_ranking_list(subMovieData['type'], self.T_count.get(), self.T_rating.get(), self.T_vote.get()) # 返回符合条件的电影信息
|
||||
self.jsonData = jsonData
|
||||
self.add_tree(list, self.treeview) # 将数据添加到tree中
|
||||
break
|
||||
|
||||
# 按钮设置为正常状态
|
||||
self.B_0['state'] = NORMAL
|
||||
self.C_type['state'] = 'readonly'
|
||||
self.T_count['state'] = NORMAL
|
||||
self.T_rating['state'] = NORMAL
|
||||
self.T_vote['state'] = NORMAL
|
||||
self.B_0_keyword['state'] = NORMAL
|
||||
self.T_vote_keyword['state'] = NORMAL
|
||||
self.B_0['text'] = '从排行榜搜索'
|
||||
|
||||
|
||||
|
||||
|
||||
def keyboard_T_vote_keyword(self, event):
|
||||
thread_it(self.searh_movie_in_keyword)
|
||||
|
||||
def searh_movie_in_keyword(self):
|
||||
"""
|
||||
从关键字中搜索符合条件的影片信息
|
||||
"""
|
||||
# 按钮设置为灰色状态
|
||||
self.clear_tree(self.treeview) # 清空表格
|
||||
self.B_0['state'] = DISABLED
|
||||
self.C_type['state'] = DISABLED
|
||||
self.T_count['state'] = DISABLED
|
||||
self.T_rating['state'] = DISABLED
|
||||
self.T_vote['state'] = DISABLED
|
||||
self.B_0_keyword['state'] = DISABLED
|
||||
self.T_vote_keyword['state'] = DISABLED
|
||||
self.B_0_keyword['text'] = '正在努力搜索'
|
||||
self.jsonData = ""
|
||||
|
||||
|
||||
|
||||
|
||||
movieObject = getMovieInRankingList(); #创建对象
|
||||
list,jsonData = movieObject.get_url_data_in_keyWord(self.T_vote_keyword.get())
|
||||
self.jsonData = jsonData
|
||||
self.add_tree(list, self.treeview) # 将数据添加到tree中
|
||||
|
||||
|
||||
|
||||
# 按钮设置为正常状态
|
||||
self.B_0['state'] = NORMAL
|
||||
self.C_type['state'] = 'readonly'
|
||||
self.T_count['state'] = NORMAL
|
||||
self.T_rating['state'] = NORMAL
|
||||
self.T_vote['state'] = NORMAL
|
||||
self.B_0_keyword['state'] = NORMAL
|
||||
self.T_vote_keyword['state'] = NORMAL
|
||||
self.B_0_keyword['text'] = '从关键字搜索'
|
||||
|
||||
|
||||
|
||||
def open_in_browser_douban_url(self, event):
|
||||
"""
|
||||
从浏览器中打开指定网页
|
||||
:param
|
||||
:return:
|
||||
"""
|
||||
item = self.treeview.selection()
|
||||
if(item):
|
||||
item_text = self.treeview.item(item, "values")
|
||||
movieName = item_text[0]
|
||||
for movie in self.jsonData:
|
||||
if(movie['title'] == movieName):
|
||||
open(movie['url'])
|
||||
|
||||
|
||||
def open_in_browser(self, event):
|
||||
"""
|
||||
从浏览器中打开指定网页
|
||||
:param
|
||||
:return:
|
||||
"""
|
||||
item = self.treeview_play_online.selection()
|
||||
if(item):
|
||||
item_text = self.treeview_play_online.item(item, "values")
|
||||
url = item_text[2]
|
||||
open(url)
|
||||
|
||||
|
||||
def open_in_browser_cloud_disk(self, event):
|
||||
"""
|
||||
从浏览器中打开指定网页
|
||||
:param
|
||||
:return:
|
||||
"""
|
||||
item = self.treeview_save_cloud_disk.selection()
|
||||
if(item):
|
||||
item_text = self.treeview_save_cloud_disk.item(item, "values")
|
||||
url = item_text[2]
|
||||
open(url)
|
||||
|
||||
|
||||
|
||||
def open_in_browser_bt_download(self, event):
|
||||
"""
|
||||
从浏览器中打开指定网页
|
||||
:param
|
||||
:return:
|
||||
"""
|
||||
item = self.treeview_bt_download.selection()
|
||||
if(item):
|
||||
item_text = self.treeview_bt_download.item(item, "values")
|
||||
url = item_text[2]
|
||||
open(url)
|
||||
|
||||
|
||||
def ui_process(self):
|
||||
"""
|
||||
Ui主程序
|
||||
:param
|
||||
:return:
|
||||
"""
|
||||
root = Tk()
|
||||
self.root = root
|
||||
# 设置窗口位置
|
||||
root.title("豆瓣电影小助手(可筛选、下载自定义电影)----吾爱破解论坛 www.52pojie.cn")
|
||||
self.center_window(root, 1000, 565)
|
||||
root.resizable(0, 0) # 框体大小可调性，分别表示x,y方向的可变性
|
||||
|
||||
|
||||
# 从排行榜 电影搜索布局开始
|
||||
# 容器控件
|
||||
labelframe = LabelFrame(root, width=660, height=300, text="搜索电影")
|
||||
labelframe.place(x=5, y=5)
|
||||
self.labelframe = labelframe
|
||||
|
||||
# 电影类型
|
||||
L_typeId = Label(labelframe, text='电影类型')
|
||||
L_typeId.place(x=0, y=10)
|
||||
self.L_typeId = L_typeId
|
||||
|
||||
#下拉列表框
|
||||
comvalue = StringVar()
|
||||
C_type = ttk.Combobox(labelframe, width=5, textvariable=comvalue, state='readonly')
|
||||
# 将影片类型输入到下拉列表框中
|
||||
jsonMovieData = loads(movieData) #json数据
|
||||
movieList = []
|
||||
for subMovieData in jsonMovieData: #对每一种类的电影题材进行操作
|
||||
movieList.append(subMovieData['title'])
|
||||
C_type["values"] = movieList #初始化
|
||||
C_type.current(9) # 选择第一个
|
||||
C_type.place(x=65, y=8)
|
||||
self.C_type = C_type
|
||||
|
||||
|
||||
# 欲获取的电影数量
|
||||
L_count = Label(labelframe, text='获取数量=')
|
||||
L_count.place(x=150, y=10)
|
||||
self.L_count = L_count
|
||||
|
||||
# 文本框
|
||||
T_count = Entry(labelframe, width=5)
|
||||
T_count.delete(0, END)
|
||||
T_count.insert(0, '500')
|
||||
T_count.place(x=220, y=7)
|
||||
self.T_count = T_count
|
||||
|
||||
|
||||
# 评分
|
||||
L_rating = Label(labelframe, text='影片评分>')
|
||||
L_rating.place(x=280, y=10)
|
||||
self.L_rating = L_rating
|
||||
|
||||
# 文本框
|
||||
T_rating = Entry(labelframe, width=5)
|
||||
T_rating.delete(0, END)
|
||||
T_rating.insert(0, '8.0')
|
||||
T_rating.place(x=350, y=7)
|
||||
self.T_rating = T_rating
|
||||
|
||||
# 评价人数
|
||||
L_vote = Label(labelframe, text='评价人数>')
|
||||
L_vote.place(x=410, y=10)
|
||||
self.L_vote = L_vote
|
||||
|
||||
# 文本框
|
||||
T_vote = Entry(labelframe, width=7)
|
||||
T_vote.delete(0, END)
|
||||
T_vote.insert(0, '100000')
|
||||
T_vote.place(x=480, y=7)
|
||||
self.T_vote = T_vote
|
||||
|
||||
|
||||
|
||||
# 查询按钮
|
||||
#lambda表示绑定的函数需要带参数，请勿删除lambda，否则会出现异常
|
||||
#thread_it表示新开启一个线程执行这个函数，防止GUI界面假死无响应
|
||||
B_0 = Button(labelframe, text="从排行榜搜索")
|
||||
B_0.place(x=560, y=10)
|
||||
self.B_0 = B_0
|
||||
|
||||
|
||||
|
||||
# 框架布局，承载多个控件
|
||||
frame_root = Frame(labelframe, width=400)
|
||||
frame_l = Frame(frame_root)
|
||||
frame_r = Frame(frame_root)
|
||||
self.frame_root = frame_root
|
||||
self.frame_l = frame_l
|
||||
self.frame_r = frame_r
|
||||
|
||||
|
||||
# 表格
|
||||
columns = ("影片名字", "影片评分", "同类排名", "评价人数")
|
||||
treeview = ttk.Treeview(frame_l, height=10, show="headings", columns=columns)
|
||||
|
||||
treeview.column("影片名字", width=210, anchor='center') # 表示列,不显示
|
||||
treeview.column("影片评分", width=210, anchor='center')
|
||||
treeview.column("同类排名", width=100, anchor='center')
|
||||
treeview.column("评价人数", width=100, anchor='center')
|
||||
|
||||
treeview.heading("影片名字", text="影片名字") # 显示表头
|
||||
treeview.heading("影片评分", text="影片评分")
|
||||
treeview.heading("同类排名", text="同类排名")
|
||||
treeview.heading("评价人数", text="评价人数")
|
||||
|
||||
|
||||
|
||||
#垂直滚动条
|
||||
vbar = ttk.Scrollbar(frame_r, command=treeview.yview)
|
||||
treeview.configure(yscrollcommand=vbar.set)
|
||||
|
||||
treeview.pack()
|
||||
self.treeview = treeview
|
||||
vbar.pack(side=RIGHT, fill=Y)
|
||||
self.vbar = vbar
|
||||
|
||||
# 框架的位置布局
|
||||
frame_l.grid(row=0, column=0, sticky=NSEW)
|
||||
frame_r.grid(row=0, column=1, sticky=NS)
|
||||
frame_root.place(x=5, y=70)
|
||||
|
||||
# 从排行榜 电影搜索布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 输入关键字 电影搜索布局开始
|
||||
|
||||
# 影片名称
|
||||
L_vote_keyword = Label(labelframe, text='影片名称')
|
||||
L_vote_keyword.place(x=0, y=40)
|
||||
#L_vote_keyword.grid(row=0,column=0)
|
||||
self.L_vote_keyword = L_vote_keyword
|
||||
|
||||
# 文本框
|
||||
T_vote_keyword = Entry(labelframe, width=53)
|
||||
T_vote_keyword.delete(0, END)
|
||||
T_vote_keyword.insert(0, '我不是药神')
|
||||
T_vote_keyword.place(x=66, y=37)
|
||||
self.T_vote_keyword = T_vote_keyword
|
||||
|
||||
|
||||
# 查询按钮
|
||||
#lambda表示绑定的函数需要带参数，请勿删除lambda，否则会出现异常
|
||||
#thread_it表示新开启一个线程执行这个函数，防止GUI界面假死无响应
|
||||
B_0_keyword = Button(labelframe, text="从关键字搜索")
|
||||
B_0_keyword.place(x=560, y=40)
|
||||
self.B_0_keyword = B_0_keyword
|
||||
|
||||
# 输入关键字 电影搜索布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 电影详情布局开始
|
||||
# 容器控件
|
||||
labelframe_movie_detail = LabelFrame(root, text="影片详情")
|
||||
labelframe_movie_detail.place(x=670, y=5)
|
||||
self.labelframe_movie_detail = labelframe_movie_detail
|
||||
|
||||
|
||||
# 框架布局，承载多个控件
|
||||
frame_left_movie_detail = Frame(labelframe_movie_detail, width=160,height=280)
|
||||
frame_left_movie_detail.grid(row=0, column=0)
|
||||
self.frame_left_movie_detail = frame_left_movie_detail
|
||||
|
||||
|
||||
frame_right_movie_detail = Frame(labelframe_movie_detail, width=160,height=280)
|
||||
frame_right_movie_detail.grid(row=0, column=1)
|
||||
self.frame_right_movie_detail = frame_right_movie_detail
|
||||
|
||||
|
||||
#影片图片
|
||||
label_img = Label(frame_left_movie_detail, text="", anchor=N)
|
||||
label_img.place(x=0,y=0) #布局
|
||||
self.label_img = label_img
|
||||
|
||||
# IMDB评分
|
||||
ft_rating_imdb = font.Font(weight=font.BOLD)
|
||||
label_movie_rating_imdb = Label(frame_left_movie_detail, text="IMDB评分", fg='#7F00FF', font=ft_rating_imdb, anchor=NW)
|
||||
label_movie_rating_imdb.place(x=0, y=250)
|
||||
self.label_movie_rating_imdb = label_movie_rating_imdb
|
||||
|
||||
# 查询按钮
|
||||
B_0_imdb = Button(frame_left_movie_detail, text="初始化")
|
||||
B_0_imdb.place(x=115, y=250)
|
||||
self.B_0_imdb = B_0_imdb
|
||||
|
||||
|
||||
#影片名字
|
||||
ft = font.Font(size=15, weight=font.BOLD)
|
||||
label_movie_name = Label(frame_right_movie_detail, text="影片名字", fg='#FF0000', font=ft,anchor=NW)
|
||||
label_movie_name.place(x=0, y=0)
|
||||
self.label_movie_name = label_movie_name
|
||||
|
||||
#影片评分
|
||||
ft_rating = font.Font(weight=font.BOLD)
|
||||
label_movie_rating = Label(frame_right_movie_detail, text="影片评价", fg='#7F00FF', font=ft_rating, anchor=NW)
|
||||
label_movie_rating.place(x=0, y=30)
|
||||
self.label_movie_rating = label_movie_rating
|
||||
|
||||
#影片年代
|
||||
ft_time = font.Font(weight=font.BOLD)
|
||||
label_movie_time = Label(frame_right_movie_detail, text="影片日期", fg='#666600', font=ft_time, anchor=NW)
|
||||
label_movie_time.place(x=0, y=60)
|
||||
self.label_movie_time = label_movie_time
|
||||
|
||||
#影片类型
|
||||
ft_type = font.Font(weight=font.BOLD)
|
||||
label_movie_type = Label(frame_right_movie_detail, text="影片类型", fg='#330033', font=ft_type, anchor=NW)
|
||||
label_movie_type.place(x=0, y=90)
|
||||
self.label_movie_type = label_movie_type
|
||||
|
||||
#影片演员
|
||||
label_movie_actor = Label(frame_right_movie_detail, text="影片演员", wraplength=135, justify = 'left', anchor=NW)
|
||||
label_movie_actor.place(x=0, y=120)
|
||||
self.label_movie_actor = label_movie_actor
|
||||
|
||||
# 电影详情布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 在线播放布局开始
|
||||
|
||||
labelframe_movie_play_online = LabelFrame(root, width=324, height=230, text="在线观看")
|
||||
labelframe_movie_play_online.place(x=5, y=305)
|
||||
self.labelframe_movie_play_online = labelframe_movie_play_online
|
||||
|
||||
# 框架布局，承载多个控件
|
||||
frame_root_play_online = Frame(labelframe_movie_play_online, width=324)
|
||||
frame_l_play_online = Frame(frame_root_play_online)
|
||||
frame_r_play_online = Frame(frame_root_play_online)
|
||||
self.frame_root_play_online = frame_root_play_online
|
||||
self.frame_l_play_online = frame_l_play_online
|
||||
self.frame_r_play_online = frame_r_play_online
|
||||
|
||||
# 表格
|
||||
columns_play_online = ("来源名称", "是否免费","播放地址")
|
||||
treeview_play_online = ttk.Treeview(frame_l_play_online, height=10, show="headings", columns=columns_play_online)
|
||||
treeview_play_online.column("来源名称", width=90, anchor='center')
|
||||
treeview_play_online.column("是否免费", width=80, anchor='center')
|
||||
treeview_play_online.column("播放地址", width=120, anchor='center')
|
||||
treeview_play_online.heading("来源名称", text="来源名称")
|
||||
treeview_play_online.heading("是否免费", text="是否免费")
|
||||
treeview_play_online.heading("播放地址", text="播放地址")
|
||||
|
||||
#垂直滚动条
|
||||
vbar_play_online = ttk.Scrollbar(frame_r_play_online, command=treeview_play_online.yview)
|
||||
treeview_play_online.configure(yscrollcommand=vbar_play_online.set)
|
||||
|
||||
treeview_play_online.pack()
|
||||
self.treeview_play_online = treeview_play_online
|
||||
vbar_play_online.pack(side=RIGHT, fill=Y)
|
||||
self.vbar_play_online = vbar_play_online
|
||||
|
||||
# 框架的位置布局
|
||||
frame_l_play_online.grid(row=0, column=0, sticky=NSEW)
|
||||
frame_r_play_online.grid(row=0, column=1, sticky=NS)
|
||||
frame_root_play_online.place(x=5, y=0)
|
||||
|
||||
# 在线播放布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 保存到云盘布局开始
|
||||
|
||||
labelframe_movie_save_cloud_disk = LabelFrame(root, width=324, height=230, text="云盘搜索")
|
||||
labelframe_movie_save_cloud_disk.place(x=340, y=305)
|
||||
self.labelframe_movie_save_cloud_disk = labelframe_movie_save_cloud_disk
|
||||
|
||||
# 框架布局，承载多个控件
|
||||
frame_root_save_cloud_disk = Frame(labelframe_movie_save_cloud_disk, width=324)
|
||||
frame_l_save_cloud_disk = Frame(frame_root_save_cloud_disk)
|
||||
frame_r_save_cloud_disk = Frame(frame_root_save_cloud_disk)
|
||||
self.frame_root_save_cloud_disk = frame_root_save_cloud_disk
|
||||
self.frame_l_save_cloud_disk = frame_l_save_cloud_disk
|
||||
self.frame_r_save_cloud_disk = frame_r_save_cloud_disk
|
||||
|
||||
# 表格
|
||||
columns_save_cloud_disk = ("来源名称", "是否有效","播放地址")
|
||||
treeview_save_cloud_disk = ttk.Treeview(frame_l_save_cloud_disk, height=10, show="headings", columns=columns_save_cloud_disk)
|
||||
treeview_save_cloud_disk.column("来源名称", width=90, anchor='center')
|
||||
treeview_save_cloud_disk.column("是否有效", width=80, anchor='center')
|
||||
treeview_save_cloud_disk.column("播放地址", width=120, anchor='center')
|
||||
treeview_save_cloud_disk.heading("来源名称", text="来源名称")
|
||||
treeview_save_cloud_disk.heading("是否有效", text="是否有效")
|
||||
treeview_save_cloud_disk.heading("播放地址", text="播放地址")
|
||||
|
||||
#垂直滚动条
|
||||
vbar_save_cloud_disk = ttk.Scrollbar(frame_r_save_cloud_disk, command=treeview_save_cloud_disk.yview)
|
||||
treeview_save_cloud_disk.configure(yscrollcommand=vbar_save_cloud_disk.set)
|
||||
|
||||
treeview_save_cloud_disk.pack()
|
||||
self.treeview_save_cloud_disk = treeview_save_cloud_disk
|
||||
vbar_save_cloud_disk.pack(side=RIGHT, fill=Y)
|
||||
self.vbar_save_cloud_disk = vbar_save_cloud_disk
|
||||
|
||||
# 框架的位置布局
|
||||
frame_l_save_cloud_disk.grid(row=0, column=0, sticky=NSEW)
|
||||
frame_r_save_cloud_disk.grid(row=0, column=1, sticky=NS)
|
||||
frame_root_save_cloud_disk.place(x=5, y=0)
|
||||
|
||||
# 保存到云盘布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# BT下载布局开始
|
||||
|
||||
labelframe_movie_bt_download = LabelFrame(root, width=324, height=230, text="影视下载")
|
||||
labelframe_movie_bt_download.place(x=670, y=305)
|
||||
self.labelframe_movie_bt_download = labelframe_movie_bt_download
|
||||
|
||||
# 框架布局，承载多个控件
|
||||
frame_root_bt_download = Frame(labelframe_movie_bt_download, width=324)
|
||||
frame_l_bt_download = Frame(frame_root_bt_download)
|
||||
frame_r_bt_download = Frame(frame_root_bt_download)
|
||||
self.frame_root_bt_download = frame_root_bt_download
|
||||
self.frame_l_bt_download = frame_l_bt_download
|
||||
self.frame_r_bt_download = frame_r_bt_download
|
||||
|
||||
# 表格
|
||||
columns_bt_download = ("来源名称", "是否有效","播放地址")
|
||||
treeview_bt_download = ttk.Treeview(frame_l_bt_download, height=10, show="headings", columns=columns_bt_download)
|
||||
treeview_bt_download.column("来源名称", width=90, anchor='center')
|
||||
treeview_bt_download.column("是否有效", width=80, anchor='center')
|
||||
treeview_bt_download.column("播放地址", width=120, anchor='center')
|
||||
treeview_bt_download.heading("来源名称", text="来源名称")
|
||||
treeview_bt_download.heading("是否有效", text="是否有效")
|
||||
treeview_bt_download.heading("播放地址", text="播放地址")
|
||||
|
||||
#垂直滚动条
|
||||
vbar_bt_download = ttk.Scrollbar(frame_r_bt_download, command=treeview_bt_download.yview)
|
||||
treeview_bt_download.configure(yscrollcommand=vbar_bt_download.set)
|
||||
|
||||
treeview_bt_download.pack()
|
||||
self.treeview_bt_download = treeview_bt_download
|
||||
vbar_bt_download.pack(side=RIGHT, fill=Y)
|
||||
self.vbar_bt_download = vbar_bt_download
|
||||
|
||||
# 框架的位置布局
|
||||
frame_l_bt_download.grid(row=0, column=0, sticky=NSEW)
|
||||
frame_r_bt_download.grid(row=0, column=1, sticky=NS)
|
||||
frame_root_bt_download.place(x=5, y=0)
|
||||
|
||||
# BT下载布局结束
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#项目的一些信息
|
||||
ft = font.Font(size=14, weight=font.BOLD)
|
||||
project_statement = Label(root, text="豆瓣电影小助手(可筛选、下载自定义电影)----吾爱破解论坛 www.52pojie.cn", fg='#FF0000', font=ft,anchor=NW)
|
||||
project_statement.place(x=5, y=540)
|
||||
self.project_statement = project_statement
|
||||
|
||||
|
||||
|
||||
#绑定事件
|
||||
treeview.bind('<<TreeviewSelect>>', self.show_movie_data) # 表格绑定选择事件
|
||||
treeview.bind('<Double-1>', self.open_in_browser_douban_url) # 表格绑定鼠标左键事件
|
||||
treeview_play_online.bind('<Double-1>', self.open_in_browser) # 表格绑定左键双击事件
|
||||
treeview_save_cloud_disk.bind('<Double-1>', self.open_in_browser_cloud_disk) # 表格绑定左键双击事件
|
||||
treeview_bt_download.bind('<Double-1>', self.open_in_browser_bt_download) # 表格绑定左键双击事件
|
||||
B_0.configure(command=lambda:thread_it(self.searh_movie_in_rating)) #按钮绑定单击事件
|
||||
B_0_keyword.configure(command=lambda:thread_it(self.searh_movie_in_keyword)) #按钮绑定单击事件
|
||||
B_0_imdb.configure(command=lambda: thread_it(self.show_IDMB_rating)) # 按钮绑定单击事件
|
||||
T_vote_keyword.bind('<Return>', handlerAdaptor(self.keyboard_T_vote_keyword)) # 文本框绑定选择事件
|
||||
project_statement.bind('<ButtonPress-1>', self.project_statement_show) # 标签绑定鼠标单击事件
|
||||
project_statement.bind('<Enter>', self.project_statement_get_focus) # 标签绑定获得焦点事件
|
||||
project_statement.bind('<Leave>', self.project_statement_lose_focus) # 标签绑定失去焦点事件
|
||||
|
||||
|
||||
|
||||
root.mainloop()
|
||||
61
README.MD
61
README.MD
|
|
@ -208,6 +208,64 @@ from contextlib import closing
|
|||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 6.爬取豆瓣排行榜电影数据(含GUI界面版)
|
||||
|
||||
|
||||
## 简介
|
||||
|
||||
这个项目源于大三某课程设计。平常经常需要搜索一些电影，但是不知道哪些评分高且评价人数多的电影。为了方便使用，就将原来的项目重新改写了。当做是对爬虫技术、可视化技术的实践了。主要是通过从排行榜和从影片关键词两种方式爬取电影数据。
|
||||
|
||||
|
||||
|
||||
## 使用教程
|
||||
|
||||
1. 打开[http://chromedriver.storage.googleapis.com/index.html][9]，根据自己的操作系统下载对应的chromedriver
|
||||
2. 打开当前面目录下的**<u>getMovieInRankingList.py</u>**，定位到第59行，将`executable_path=/Users/bird/Desktop/chromedriver.exe`修改成你自己的chromedriver路径
|
||||
3. 打开pycharm，依次安装以下包
|
||||
- pip install Pillow
|
||||
- pip install selenium
|
||||
|
||||
|
||||
|
||||
## 演示图片
|
||||
|
||||
/example_rating.png)
|
||||
|
||||
/example_keyword.png)
|
||||
|
||||
|
||||
|
||||
## 包含功能
|
||||
|
||||
- [x] 根据关键字搜索电影
|
||||
- [x] 根据排行榜(TOP250)搜索电影
|
||||
- [x] 显示IMDB评分及其他基本信息
|
||||
- [x] 提供多个在线视频站点，无需vip
|
||||
- [x] 提供多个云盘站点搜索该视频，以便保存到云盘
|
||||
- [x] 提供多个站点下载该视频
|
||||
- [ ] 等待更新
|
||||
|
||||
|
||||
## 存在问题
|
||||
|
||||
目前没有加入反爬虫策略，如果运行出现403 forbidden提示，则说明暂时被禁止，解决方式如下：
|
||||
|
||||
- 加入cookies
|
||||
- 采用随机延时方式
|
||||
- 采用IP代理池方式(较不稳定)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 补充
|
||||
|
||||
项目持续更新，欢迎您[star本项目][5]
|
||||
|
|
@ -229,4 +287,5 @@ from contextlib import closing
|
|||
[5]:https://github.com/shengqiangzhang/examples-of-web-crawlers
|
||||
[6]:http://opensource.org/licenses/MIT
|
||||
[7]:https://raw.githubusercontent.com/shengqiangzhang/examples-of-web-crawlers/master/3.%E6%B7%98%E5%AE%9D%E5%B7%B2%E4%B9%B0%E5%88%B0%E7%9A%84%E5%AE%9D%E8%B4%9D%E6%95%B0%E6%8D%AE%E7%88%AC%E8%99%AB(%E5%B7%B2%E6%A8%A1%E6%8B%9F%E7%99%BB%E5%BD%95)/example.gif
|
||||
[8]:http://paper.meiyuan.in/
|
||||
[8]:http://paper.meiyuan.in/
|
||||
[9]:http://chromedriver.storage.googleapis.com/index.html
|
||||
|
|
|
|||
Loading…
Reference in New Issue