python 电影下载链接爬虫

V1.0

功能：从比较知名的几个电影下载网站爬取下载链接，并自动打印出来：

代码：

# -*- coding: utf8 -*-
from bs4 import BeautifulSoup
import requests, lxml
from urllib.parse import quote
import re


def get_name():
    while 1:
        moviename = input('请输入要查找的电影名
->')
        moviename_quote = quote(moviename.encode('gb2312'))
        get_url_from_ygdy(moviename_quote)
        get_url_from_bttiantang(moviename)
        get_url_from_dytt(moviename_quote)


def get_url_from_ygdy(moviename):
    baseurl = 'http://s.dydytt.net/plus/search.php?kwtype=0&keyword='
    url = baseurl + str(moviename)
    content = BeautifulSoup(requests.get(url).content.decode('gb2312', 'ignore'), 'lxml')
    first_page = content.find_all('td', width="30")
    movie_infos = content.find_all('td', width="55%")
    if movie_infos.__len__() == 0:
        print('查无此电影，请检查后重试')
        return
    else:
        print('阳光电影搜索结果:')
        if first_page.__len__() == 0:
            for movie_info in movie_infos:
                get_info(movie_info, moviename)
        else:
            last_page_url = first_page[1].find('a').get('href') + '"'
            pattern = re.compile('PageNo=(.*?)"')
            pnt = re.findall(pattern, last_page_url)
            for i in range(int(pnt[0])):
                print('第', i + 1, '页:')
                page_url = url + '&PageNo=' + str(i + 1)
                pagecontent = BeautifulSoup(requests.get(page_url).content.decode('gb2312', 'ignore'), 'lxml')
                movie_infos = pagecontent.find_all('td', width='55%')
                for movie_info in movie_infos:
                    get_info(movie_info, moviename)


def get_info(movie_info, name):
    movie_url = movie_info.find('a').get('href')
    moviename = movie_info.text
    if '游戏' not in name and '游戏' in moviename:
        return
    else:
        print('电影名:', moviename)
        url = 'http://www.ygdy8.com' + movie_url
        info = BeautifulSoup(requests.get(url).content.decode('gbk', 'ignore'), 'lxml')
        download = info.find_all('td', style="WORD-WRAP: break-word")
        print('下载链接:')
        if download.__len__() == 1:
            print(download[0].find('a').string)
        else:
            for each in range(download.__len__()):
                print('链接', each + 1, ':', download[each].find('a').string)
        print('
')


def get_url_from_bttiantang(moviename):
    baseurl = 'http://www.bttiantang.com/s.php?q=' + str(moviename)
    page_content = requests.get(baseurl).content.decode('utf8', 'ignore')
    pattern = re.compile('</b>条<b>(.*?)</b>')
    pagenum_info = re.findall(pattern, page_content)
    page_content = BeautifulSoup(page_content, 'lxml')
    content = page_content.find_all('p', class_="tt cl")
    if content.__len__() == 0:
        print('查无此电影，请检查后重试')
        return
    else:
        print('BT天堂搜索结果:')
        if pagenum_info.__len__() == 0:
            for each in content:
                get_movieinfo(each, moviename)
        else:
            for i in range(int(pagenum_info[0])):
                print('第', i + 1, '页:')
                page_url = baseurl + '&PageNo=' + str(i + 1)
                page_content = BeautifulSoup(requests.get(page_url).content.decode('utf8', 'ignore'), 'lxml')
                content = page_content.find_all('p', class_="tt cl")
                for each in content:
                    get_movieinfo(each, moviename)


def get_movieinfo(movie_content, name):
    url = 'http://www.bttiantang.com/' + movie_content.find('a').get('href')
    moviename = movie_content.text
    if '游戏' not in name and '游戏' in moviename:
        return
    print('电影名:', moviename)
    info = BeautifulSoup(requests.get(url).content.decode('utf8', 'ignore'), 'lxml')
    links = info.find_all('div', class_='tinfo')
    print('下载链接:')
    i = 0
    for each in links:
        i += 1
        print('链接' + str(i) + ':')
        print('http://www.bttiantang.com' + each.find('a').get('href'))


def get_url_from_dytt(moviename):
    baseurl = 'http://www.dytt.com/search.asp?searchword=' + str(moviename)
    content = requests.get(baseurl).content.decode('gbk', 'ignore')
    pattern = re.compile('下一页.*?href.*?page=(.*?)&')
    result = re.findall(pattern, content)
    content = BeautifulSoup(content, 'lxml')
    items = content.find_all('p', class_='s1')
    if items.__len__() == 1:
        print('查无此电影，请检查后重试')
        return
    else:
        print('电影淘淘搜索结果:')
        if result.__len__() == 0:
            for i in range(items.__len__() - 1):
                get_movieinfo_from_dytt(items[i + 1], moviename)
        else:
            for i in range(int(result[0])):
                print('第', i + 1, '页:')
                url = baseurl + '&page=' + str(i + 1)
                page_content = BeautifulSoup(requests.get(url).content.decode('gbk', 'ignore'), 'lxml')
                items = page_content.find_all('p', class_='s1')
                for i in range(items.__len__() - 1):
                    get_movieinfo_from_dytt(items[i + 1], moviename)


def get_movieinfo_from_dytt(item, name):
    moviename = item.find('a').text
    movieurl = 'http://www.dytt.com' + item.find('a').get('href')
    if '游戏' not in name and '游戏' in moviename:
        return
    print('电影名:', moviename)
    pagecontent = requests.get(movieurl).content.decode('gbk', 'ignore')
    links = re.findall(re.compile('ed2k:(.*?)|/'), pagecontent)
    i = 0
    print('下载链接:')
    if links.__len__() != 0:
        for link in links:
            i += 1
            print('链接' + str(i) + ':', 'ed2k://|file|' + link + '|/')
    else:
        links = re.findall(re.compile('http:(.*?)torrent'), pagecontent)
        if links.__len__() != 0:
            for link in links:
                i += 1
                print('链接' + str(i) + ':', 'http:' + link + 'torrent')
        else:
            links = re.findall(re.compile('ftp:(.*?)mkv'), pagecontent)
            for link in links:
                i += 1
                print('链接' + str(i) + ':', 'ftp:' + link + 'mkv')


if __name__ == '__main__':
    get_name()

 运行结果：