[宅男福利] 电影天堂最新合集、搜索脚本 [原创]
宅男福利第四波 带你逃离无止境的广告
多线程电影天堂最新资源爬取脚本、电影搜索脚本
PS:方便大家使用写到了HTML中生成表格。
环境: Python3
最新电影爬取代码
# -*- coding: utf-8 -*-
# @Time : 2018/3/5 下午2:43
# @Author : MyPuppet
# @File : ygdy8.py
# @Software: PyCharm
import random
import threading
import requests as req
from lxml import etree
from queue import Queue
BASE_URL_COM = 'http://www.ygdy8.com'
BASE_URL_NET = 'http://www.ygdy8.net'
THREADS = 20
PAGE_TOTAL = 100
HEAD = '<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><title>阳光电影 - 电影天堂</title><link href="https://cdn.bootcss.com/bootstrap/4.0.0/css/bootstrap.min.css" rel="stylesheet"></head><body><table class="table"><thead class="thead-dark"><tr><th scope="col">#</th><th scope="col">电影名</th><th scope="col">下载地址</th></tr></thead><tbody class="table-hover">'
FOOT = '</tbody></table></body></html>'
count = 1
def get_headers():
user_agent_list = [
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1',
'Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24'
]
UA = random.choice(user_agent_list)
headers = {'User-Agent': UA}
return headers
def get_url(list_queue, url_queue):
while True:
url = list_queue.get()
try:
res = req.get(url, headers=get_headers())
res.encoding = res.apparent_encoding
html = etree.HTML(res.text)
tags = html.xpath('//div[@class="co_content8"]/ul//a')
for tag in tags:
href = tag.get('href')
url_queue.put(href, 1)
print('[Subscribe] [%s]' % href)
except:
print('[Subscribe Error] %s' % url)
list_queue.task_done()
def get_list(list_queue):
lists = [i for i in range(1, PAGE_TOTAL + 1)]
list_url = 'http://www.ygdy8.com/html/gndy/dyzz/list_23_%d.html'
for i in lists:
url = list_url % i
list_queue.put(url, 1)
def parse_download(url):
res = req.get(url, headers=get_headers())
res.encoding = res.apparent_encoding
html = etree.HTML(res.text)
title = html.xpath('//div[@class="bd3r"]//div[@class="title_all"]/h1/font')[0].text
downloads = html.xpath('//div[@id="Zoom"]//table//a/@href')
return title, downloads
def parse_html(url_queue, result_file):
while True:
global count
url_path = url_queue.get()
try:
try:
url = BASE_URL_COM + url_path
(title, downloads) = parse_download(url)
except:
url = BASE_URL_NET + url_path
(title, downloads) = parse_download(url)
download = '<hr>'.join(downloads)
tr = '<tr><th scope="row">%d</th><td>%s</td><td>%s</td></tr>' % (count, title, download)
result_file.write(tr)
print('[OK][%d] %s' % (count, title))
count = count + 1
except:
print('[Parse error] %s' % url_path)
url_queue.task_done()
def thread(thread_name, target, args):
for i in range(THREADS):
t = threading.Thread(target=target, args=args)
t.setDaemon(True)
t.start()
thread_name.join()
def main():
list_queue = Queue()
url_queue = Queue()
get_list(list_queue)
thread(list_queue, get_url, (list_queue, url_queue))
result_file = open('result.html', 'w')
result_file.write(HEAD)
thread(url_queue, parse_html, (url_queue, result_file))
result_file.write(FOOT)
result_file.close()
print('End... 老铁记得顶我(TieZi)\nEnd... 老铁记得顶我(TieZi)\nEnd... 老铁记得顶我(TieZi)')
if __name__ == '__main__':
main()
# -*- coding: utf-8 -*-
# @Time : 2018/3/6 下午12:00
# @Author : MyPuppet
# @File : search.py
# @Software: PyCharm
import sys
import random
import requests as req
from urllib import parse
from lxml import etree
from multiprocessing import Pool
BASE_URL = 'http://www.ygdy8.com'
SEARCH_URL = 'http://s.ygdy8.com/plus/so.php?kwtype=0&searchtype=title&pagesize=1000&keyword='
# 关键字需要URL字符编码
def get_headers():
user_agent_list = [
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1',
'Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24'
]
ua = random.choice(user_agent_list)
headers = {'User-Agent': ua}
return headers
def search(keyword):
keyword = parse.quote(keyword.encode("gbk"))
url = SEARCH_URL + keyword
res = req.get(url, headers=get_headers())
res.encoding = res.apparent_encoding
html = etree.HTML(res.text)
tags = html.xpath('//div[@class="co_content8"]/ul//a')
result_urls = []
for tag in tags:
url = BASE_URL + tag.get('href')
result_urls.append(url)
return result_urls
def parse_html(url):
res = req.get(url, headers=get_headers())
res.encoding = res.apparent_encoding
html = etree.HTML(res.text)
title = html.xpath('//div[@class="bd3r"]//div[@class="title_all"]/h1/font')[0].text
downloads = html.xpath('//div[@id="Zoom"]//table//a/@href')
print('[%s]' % title)
for download in downloads:
print('[下载链接] [%s]' % download)
print('\n|----------------------------------------------------------|\n')
if __name__ == '__main__':
if len(sys.argv) < 2:
print("Usage: python %s movie_name" % sys.argv[0])
exit(-1)
urls = search(sys.argv[1])
pool = Pool()
pool.map(parse_html, urls)
生成后的HTML表格
电影搜索效果
[补图]爬取的下载链接含FTP和磁力链接,片源有磁力链接就会被爬取
爬取结果
搜索结果
上波福利大佬们要视频,喏~你们的视频
自评 TCV 1,有没有都行不过这次确实读懂了多线程!
有钱的捧个钱场没钱的捧个人场。
评论122次
用Python写爬虫还真的方便与简洁
要是把几个大的资源站爬下来整合一下 是不是资源大亨了
老大这一波走得稳!赞一个。
膜拜大佬 学xi了
很是厉害,以后nas可以实现
厉害了,正在学xi。
不能筛选吗
技术宅拯救世界啊,要是再加个调用transmission接口添加下载任务的功能就更好了,以后想看什么电影美剧先弄个关注列表,每天自动取网站上爬,爬到新的电影和美剧就自动下载。。。
老哥贼吻
很想知道你的-20TuBi怎么做到的,哪里能赊账?
老哥贼吻
这个厉害了,学xi中。
能够通配其他网站起来咋样
可以从其他网站爬取吗
改下规则问题应该不大
我修改下测试
正在学xipython,学xi了,看来python越来越强大了哈
输出到html学xi了
经常在这站上 下载大片 看哈
广告太多了,进入页面全屏广告,搜索输入框事件广告,列表页全屏广告
电影站 都是很多收费广告
看到宅男 我进来了。。。
老兄 NB 谢谢分享
能否弄个91PRON 和xvideos的呢 !
大胸弟,贴出地址才能爬啊,贡献出你收藏的地址
宅男不是看普通电影的,求大片地址。。 手动滑稽