tkinter与爬虫的有机结合，视频爬虫GUI实现（新增下载功能）

更新了GUI版本的下载功能，相较于GitHub版本的代码，在GUI版本弃用了一部分资源，可能对检索结果产生部分影响。

下图为2020-08-07更新后的效果图，可直接跳到后面查看。

这是非gui版的爬虫源码，功能更强大，支持视频下载，逻辑也更加完整，感兴趣可以看看

https://github.com/iskangkanga/PiracyVideo

简单实现GUI版本的视频爬虫

效果图：

 

代码：

import re
from service.geter import get_response
import requests
import traceback
from tkinter import *


def get_source():
    # 响应第一个button，仅获取资源并输出到gui
    result = ''
    search_url = 'https://www.yszxwang.com/search.php'
    data = {
        'searchword': inp1.get()
    }
    resp = requests.post(search_url, data=data, timeout=15)
    # print(resp.text)
    # 若网站检索无结果，直接返回错误提示并关闭爬虫
    if '对不起，没有找到' in resp.text:
        txt.insert(END, 'ERROR, 网站检索无此结果！' + '\n')
        return
    # 进入搜索详情页，获取详情页链接
    urls = re.findall('href="(/[a-z]+?/.*?\d+/)"', resp.text)
    titles = re.findall('<h3><a.*?>(.*?)</a></h3>', resp.text)
    types = re.findall('<h3><a href="/(.*?)/.*?\d+/">.*?</a></h3>', resp.text)
    type_list = []
    for t in types:
        if t == 'tv':
            t = '电视剧'
        elif t == 'dm':
            t = '动漫'
        elif t == 'dy':
            t = '电影'
        elif t == 'zy':
            t = '综艺'
        type_list.append(t)
    # 暂时已发现 tv：剧集  dm：动漫  dy：电影  zy：综艺
    # print(titles)
    for url in urls:
        if len(url) > 60:
            urls.remove(url)
    r_urls = []
    for u in urls:
        if u not in r_urls:
            r_urls.append(u)
    txt.insert(END, '已为你检索到结果如下：' + '\n')
    for i, title in enumerate(titles):
        txt.insert(END, str(i+1) + ' ' + title + ' ' + type_list[i] + '\n')


def get_source1():
    # 获取资源并返回到方法
    result = ''
    search_url = 'https://www.yszxwang.com/search.php'
    data = {
        'searchword': inp1.get()
    }
    resp = requests.post(search_url, data=data, timeout=15)
    urls = re.findall('href="(/[a-z]+?/.*?\d+/)"', resp.text)
    for url in urls:
        if len(url) > 60:
            urls.remove(url)
    r_urls = []
    for u in urls:
        if u not in r_urls:
            r_urls.append(u)
    return r_urls


def begin_parse():
    # 响应第二个button，开始解析
    f_type = inp3.get()
    choice = int(inp2.get())
    r_urls = get_source1()
    detail_url = 'https://www.yszxwang.com' + r_urls[choice - 1]
    if f_type == '1':
        # 单剧集解析
        parse_alone(detail_url)
    else:
        # 多剧集解析
        parse_many(detail_url)


def parse_alone(detail_url):
    resp = get_response(detail_url)
    if not resp:
        txt2.insert(END, '失败' + '\n')
        return
    play_urls = re.findall('a title=.*? href=\'(.*?)\' target="_self"', resp)
    play_url = get_real_url(play_urls)
    if 'http' in play_url:
        txt2.insert(END, "复制到浏览器播放" + '\n')
        txt2.insert(END, play_url + '\n')
    else:
        txt2.insert(END, "解析失败" + '\n')


def get_real_url(play_urls):
    for i, play_page_url in enumerate(play_urls):
        play_page_url = 'https://www.yszxwang.com' + play_page_url
        resp1 = get_response(play_page_url)
        if resp1:
            data_url = re.search('var now="(http.*?)"', resp1).group(1).strip()
            resp2 = get_response(data_url)
            if resp2:
                return data_url
    return 'defeat'


def parse_many(detail_url):
    all_play_list, play_num = get_all_source(detail_url)
    many_real_url = get_many_real_url(all_play_list, play_num)
    if isinstance(many_real_url,list):
        txt2.insert(END, '已为你检索到结果如下：' + '\n')
        txt2.insert(END, "复制到浏览器播放" + '\n')
        for i, r in enumerate(many_real_url):
            txt2.insert(END, "第" + str(i+1) + '集' + ' ' + r + '\n')
    else:
        txt2.insert(END, "解析失败" + '\n')


def get_many_real_url(all_play_list, play_num):
    for i, play_list in enumerate(all_play_list):
        many_data_url = []
        for j, play_page_url in enumerate(play_list):
            play_page_url = 'https://www.yszxwang.com' + play_page_url
            resp1 = get_response(play_page_url)
            if resp1:
                data_url = re.search('var now="(http.*?)"', resp1).group(1).strip()