zoukankan html css js c++ java

【宅男宅女们的福音】电影天堂最新电影爬取及搜索脚本

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。
线程可以在脚本里直接改，测试线程为30时IP可能会被限制访问。[阳光电影是电影天堂的马甲]

环境: Python3

最新电影爬取代码

# -*- coding: utf-8 -*-
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)
End... 老铁记得顶我(TieZi)
End... 老铁记得顶我(TieZi)')


if __name__ == '__main__':
    main()

搜索电影代码

# -*- coding: utf-8 -*-
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('
|----------------------------------------------------------|
')



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)