|
| 1 | +# -*-coding:utf-8 -*- |
| 2 | +# Website: http://cuijiahua.com |
| 3 | +# Author: Jack Cui |
| 4 | +# Date: 2018.6.9 |
| 5 | + |
| 6 | +import requests, json, re, sys, os, urllib, argparse, time |
| 7 | +from urllib.request import urlretrieve |
| 8 | +from contextlib import closing |
| 9 | +from urllib import parse |
| 10 | +import xml2ass |
| 11 | + |
| 12 | +class BiliBili: |
| 13 | + def __init__(self, dirname, keyword): |
| 14 | + self.dn_headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.167 Safari/537.36', |
| 15 | + 'Accept': '*/*', |
| 16 | + 'Accept-Encoding': 'gzip, deflate, br', |
| 17 | + 'Accept-Language': 'zh-CN,zh;q=0.9', |
| 18 | + 'Referer': 'https://search.bilibili.com/all?keyword=%s' % parse.quote('猫')} |
| 19 | + |
| 20 | + self.search_headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.167 Safari/537.36', |
| 21 | + 'Accept-Language': 'zh-CN,zh;q=0.9', |
| 22 | + 'Accept-Encoding': 'gzip, deflate, br', |
| 23 | + 'Accept': 'application/json, text/plain, */*'} |
| 24 | + |
| 25 | + self.video_headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.167 Safari/537.36', |
| 26 | + 'Accept-Language': 'zh-CN,zh;q=0.9', |
| 27 | + 'Accept-Encoding': 'gzip, deflate, br', |
| 28 | + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'} |
| 29 | + |
| 30 | + self.danmu_header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.167 Safari/537.36', |
| 31 | + 'Accept': '*/*', |
| 32 | + 'Accept-Encoding': 'gzip, deflate, br', |
| 33 | + 'Accept-Language': 'zh-CN,zh;q=0.9'} |
| 34 | + |
| 35 | + self.sess = requests.Session() |
| 36 | + |
| 37 | + self.dir = dirname |
| 38 | + |
| 39 | + def video_downloader(self, video_url, video_name): |
| 40 | + """ |
| 41 | + 视频下载 |
| 42 | + Parameters: |
| 43 | + video_url: 带水印的视频地址 |
| 44 | + video_name: 视频名 |
| 45 | + Returns: |
| 46 | + 无 |
| 47 | + """ |
| 48 | + size = 0 |
| 49 | + with closing(self.sess.get(video_url, headers=self.dn_headers, stream=True, verify=False)) as response: |
| 50 | + chunk_size = 1024 |
| 51 | + content_size = int(response.headers['content-length']) |
| 52 | + if response.status_code == 200: |
| 53 | + sys.stdout.write(' [文件大小]:%0.2f MB\n' % (content_size / chunk_size / 1024)) |
| 54 | + video_name = os.path.join(self.dir, video_name) |
| 55 | + with open(video_name, 'wb') as file: |
| 56 | + for data in response.iter_content(chunk_size = chunk_size): |
| 57 | + file.write(data) |
| 58 | + size += len(data) |
| 59 | + file.flush() |
| 60 | + |
| 61 | + sys.stdout.write(' [下载进度]:%.2f%%' % float(size / content_size * 100) + '\r') |
| 62 | + # sys.stdout.flush() |
| 63 | + if size / content_size == 1: |
| 64 | + print('\n') |
| 65 | + else: |
| 66 | + print('链接异常') |
| 67 | + |
| 68 | + def search_video(self, search_url): |
| 69 | + """ |
| 70 | + 搜索接口 |
| 71 | + Parameters: |
| 72 | + search_url: 带水印的视频地址 |
| 73 | + Returns: |
| 74 | + titles：视频名列表 |
| 75 | + arcurls: 视频播放地址列表 |
| 76 | + """ |
| 77 | + req = self.sess.get(url=search_url, headers=self.search_headers, verify=False) |
| 78 | + html = json.loads(req.text) |
| 79 | + videos = html['result'] |
| 80 | + titles = [] |
| 81 | + arcurls = [] |
| 82 | + for video in videos: |
| 83 | + titles.append(video['title'].replace('<em class="keyword">','').replace('</em>','')) |
| 84 | + arcurls.append(video['arcurl']) |
| 85 | + return titles, arcurls |
| 86 | + |
| 87 | + def get_download_url(self, arcurl): |
| 88 | + """ |
| 89 | + 获取视频下载地址 |
| 90 | + Parameters: |
| 91 | + arcurl: 视频播放地址 |
| 92 | + oid：弹幕地址参数 |
| 93 | + Returns: |
| 94 | + download_url：视频下载地址 |
| 95 | + """ |
| 96 | + req = self.sess.get(url=arcurl, headers=self.video_headers, verify=False) |
| 97 | + pattern = '.__playinfo__=(.*)</script><script>window.__INITIAL_STATE__=' |
| 98 | + try: |
| 99 | + infos = re.findall(pattern, req.text)[0] |
| 100 | + except: |
| 101 | + return '','' |
| 102 | + html = json.loads(infos) |
| 103 | + durl = html['durl'] |
| 104 | + print(durl) |
| 105 | + download_url = durl[0]['url'] |
| 106 | + if 'mirrork' in download_url: |
| 107 | + oid = download_url.split('/')[6] |
| 108 | + else: |
| 109 | + oid = download_url.split('/')[7] |
| 110 | + if len(oid) >= 10: |
| 111 | + oid = download_url.split('/')[6] |
| 112 | + return download_url, oid |
| 113 | + |
| 114 | + |
| 115 | + def download_xml(self, danmu_url, danmu_name): |
| 116 | + """ |
| 117 | + 获取视频XML原生弹幕 |
| 118 | + Parameters: |
| 119 | + danmu_url: 弹幕地址 |
| 120 | + danmu_name：弹幕xml文件保存名 |
| 121 | + Returns: |
| 122 | + 无 |
| 123 | + """ |
| 124 | + with closing(self.sess.get(danmu_url, headers=self.danmu_header, stream=True, verify=False)) as response: |
| 125 | + if response.status_code == 200: |
| 126 | + with open(danmu_name, 'wb') as file: |
| 127 | + for data in response.iter_content(): |
| 128 | + file.write(data) |
| 129 | + file.flush() |
| 130 | + else: |
| 131 | + print('链接异常') |
| 132 | + |
| 133 | + def get_danmu(self, oid, filename): |
| 134 | + """ |
| 135 | + 下载弹幕 |
| 136 | + Parameters: |
| 137 | + oid: 弹幕oid |
| 138 | + filename: 弹幕保存前缀名 |
| 139 | + Returns: |
| 140 | + 无 |
| 141 | + """ |
| 142 | + danmu_url = 'https://api.bilibili.com/x/v1/dm/list.so?oid={}'.format(oid) |
| 143 | + danmu_name = os.path.join(self.dir, filename + '.xml') |
| 144 | + danmu_ass = os.path.join(self.dir, filename + '.ass') |
| 145 | + self.download_xml(danmu_url, danmu_name) |
| 146 | + time.sleep(0.5) |
| 147 | + xml2ass.Danmaku2ASS(danmu_name, danmu_ass, 1280, 720) |
| 148 | + # os.remove(danmu_name) |
| 149 | + |
| 150 | + def search_videos(self, keyword, pages): |
| 151 | + """ |
| 152 | + 搜索视频 |
| 153 | + Parameters: |
| 154 | + keyword: 搜索关键字 |
| 155 | + pages：下载页数 |
| 156 | + Returns: |
| 157 | + 无 |
| 158 | + """ |
| 159 | + if self.dir not in os.listdir(): |
| 160 | + os.mkdir(self.dir) |
| 161 | + for page in range(1, pages+1): |
| 162 | + search_url = 'https://search.bilibili.com/api/search?search_type=video&keyword={}&order=totalrank&duration=1&tids=0&page={}'.format(keyword, page) |
| 163 | + titles, arcurls = self.search_video(search_url) |
| 164 | + for index, arcurl in enumerate(arcurls): |
| 165 | + title = titles[index] |
| 166 | + for c in u'´☆❤◦\/:*?"<>|': |
| 167 | + title = title.replace(c, '') |
| 168 | + if title + '.flv' not in os.listdir(self.dir): |
| 169 | + download_url, oid = self.get_download_url(arcurl) |
| 170 | + if download_url != '' and oid != '': |
| 171 | + print('第[ %d ]页:视频[ %s ]下载中:' % (page, title)) |
| 172 | + self.video_downloader(download_url, title + '.flv') |
| 173 | + print('视频下载完成!') |
| 174 | + self.get_danmu(oid, title) |
| 175 | + print('弹幕下载完成!') |
| 176 | + |
| 177 | +if __name__ == '__main__': |
| 178 | + |
| 179 | + if len(sys.argv) == 1: |
| 180 | + sys.argv.append('--help') |
| 181 | + |
| 182 | + parser = argparse.ArgumentParser() |
| 183 | + parser.add_argument('-d', '--dir', required=True, help=_('download path')) |
| 184 | + parser.add_argument('-k', '--keyword', required=True, help=_('search content')) |
| 185 | + parser.add_argument('-p', '--pages', required=True, help=_('the number of pages for downloading'), type=int, default=1) |
| 186 | + |
| 187 | + args = parser.parse_args() |
| 188 | + B = BiliBili(args.dir,args.keyword) |
| 189 | + B.search_videos(args.keyword, args.pages) |
| 190 | + |
| 191 | + print('全部下载完成!') |
0 commit comments