Python_6v电影爬虫

本文来源吾爱破解论坛

大噶好，我是过儿，初次来到论坛，作为小白分享一下没事胡乱捣鼓的东西：Python实现爬去www.66s.cc网站的电影资源

代码如下：
www.66s.cc
[Python] 纯文本查看 复制代码

import requests
from lxml import etree
import re
import sys
from gogogo import model

headers = {
    "Cookie": "UM_distinctid=168da7d834b51f-07e1b88232dad6-49423f1f-144000-168da7d834c900; CNZZDATA1273922090=1881870440-1549849873-https%253A%252F%252Fwww.66s.cc%252F%7C1549865717; tinmkcheckplkey=1549871167%2Cd7f8997e266f5fc265bacd8b3a9dfa1c%2Cfbd0b9d6b9ae7c4e83056665281a6f3f; CNZZDATA1273606887=1885359854-1549850294-%7C1549867557",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.90 Safari/537.36 2345Explorer/9.6.0.18627",
}

def index(url,num):
    if num == 1:
        url_ = url
        obj = model(url_,"//div[@class='post_hover']/div[@class='thumbnail']/a/@href")
        return obj
    elif num == 2:
        url_ = url + "qian50m.html"
        obj = model(url_, "//div[@id='tab-content']/ul[@class='']/li/a/@href")
        return obj
    elif num == 3:
        url_ = url + "qian50m.html"
        obj = model(url_, "//div[@id='tab-content']/ul[@class='hide'][1]/li/a/@href")
        return obj
    else:
        print("输入有误，程序退出！")
        sys.exit()

def movie(url):
    response = requests.get(url=url,headers=headers)
    text = response.content.decode("utf-8")
    html = etree.HTML(text)
    movie_name = html.xpath("//h1/text()")[1]
    try:
        movie_urls = html.xpath("//div[@class='widget box row'][2]/a/@href")[0]
        return movie_name, movie_urls
    except:
        return movie_name,None

def m3u8(name,url):
    response = requests.get(url=url, headers=headers)
    text = response.content.decode("utf-8")
    name = name
    m3u8 = re.findall(r"a:'(.*?)',", text, re.S)[0]
    return name,m3u8

def mp4(name,url):
    dict = {}
    url = url
    response = requests.get(url=url, headers=headers)
    text = response.text
    # print(url)
    m3u8 = re.findall(r"/ppvod/(.*?).m3u8", text, re.S)[0]
    m3u8 = "https://vip2.pp63.org/ppvod/" + m3u8 + ".m3u8"
    # print(m3u8)
    name = name
    print("获取成功：        " + name + "   ==>   " + "爬取完毕，已保存至运行目录！" + "\n")
    dict[name] = m3u8
    return dict

if __name__ == '__main__':
    url = input("请输入网址：")
    str_ = "1.首页推荐" + "\n" + "2.电影" + "\n" + "3.电视剧" + "\n" + "请选择："     # urls = index("https://www.66s.cc/")

    for i in str_:
        print(i, end="")
    num = int(input())

    urls = index(url,num)
    for url in urls:
        movie_name = movie(url)[0]
        movie_url = movie(url)[1]
        if movie_url is not None:
            m3u8_name = m3u8(name=movie_name,url=movie_url)[0]
            m3u8_url = m3u8(name=movie_name,url=movie_url)[1]
            mp4s = mp4(m3u8_name,m3u8_url)

            for name, url in mp4s.items():
                if num == 1:
                    with open("首页推荐.txt", "a") as f:
                        f.write(str(name + "   ===>   " + "https://www.115z.com/video?url=" + str(url)).encode(
                            "gbk").decode("gbk") + "\n\n")
                elif num == 2:
                    with open("电影.txt", "a") as f:
                        f.write(str(name + "   ===>   " + "https://www.115z.com/video?url=" + str(url)).encode(
                            "gbk").decode("gbk") + "\n\n")
                elif num == 3:
                    with open("电视剧.txt", "a") as f:
                        f.write(str(name + "   ===>   " + "https://www.115z.com/video?url=" + str(url)).encode(
                            "gbk").decode("gbk") + "\n\n")

import requests
from lxml import etree

headers = {
    "Cookie": "UM_distinctid=168da7d834b51f-07e1b88232dad6-49423f1f-144000-168da7d834c900; CNZZDATA1273922090=1881870440-1549849873-https%253A%252F%252Fwww.66s.cc%252F%7C1549865717; tinmkcheckplkey=1549871167%2Cd7f8997e266f5fc265bacd8b3a9dfa1c%2Cfbd0b9d6b9ae7c4e83056665281a6f3f; CNZZDATA1273606887=1885359854-1549850294-%7C1549867557",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.90 Safari/537.36 2345Explorer/9.6.0.18627",
}

def model(url,xpath):
    response = requests.get(url=url, headers=headers)
    text = response.content.decode("utf-8")
    html = etree.HTML(text)
    index_urls = html.xpath(xpath)
    return index_urls

import re
import urllib.request
import os

# def myReportHook(count, blockSize, totalSize):
# #      print(count, blockSize, totalSize)

if __name__ == '__main__':
    with open("cl9SheFa.m3u8",'r') as f:
        text = f.read()

    parse_text = re.sub(r"\n/","\nhttps://vip2.pp63.org/",text)

    html = re.sub(r"#.*,\n","",parse_text)

    urls = html.split("\n")[4:-2]

    print("共有" + str(len(urls)) + "个ts文件，开始下载！\n\n")

    # print(urls)

    for index,url in enumerate(urls):
        try:
            urllib.request.urlretrieve(url,str(index + 1) + ".ts")
            print("第" + str(index + 1) + "下载完成!")
        except:
            print("\n\n你没网了，请检查网络！" + "          第" + str(index + 1) + "下载失败!\n")
            # break

    for num in range(len(urls)):
        print(num)

os.system("copy /b *.ts 电影.mp4")
os.system('del /Q *.ts')