public async Task GetVideoUrlForFeelAgain()
{
var result = await _videoUrlCrawler.GetUrlBySingleContentId(
await _videoInfoCrawler.GetVideoInfo("av349183"));
Assert.NotNull(result);
Assert.NotEqual(0, result.Durl.Count);
_PrintUrl(result);
}
public async Task WhatMakesYouBeautifulMvTest()
{
// Video URL: http://www.bilibili.com/video/av3355175/
// Video is "What makes ou beautiful", Content ID 5309628
Console.WriteLine("[TEST] Running test for av3355175...");
var videoInfoForAv3355175 = await videoInfoCrawler.GetVideoInfo("av3355175");
// Validate the beautiful result and see if it correct content ID
Assert.NotNull(videoInfoForAv3355175);
Assert.True(videoInfoForAv3355175.ContentId.Equals("5309628"));
}
/// <summary>
/// Generate video link
/// Note:
/// 1. UserAgent (MSIE10) and Referrer must be set to the downloader, otherwise server will return 500
/// 2. Exception may be raised if something goes wrong (e.g. no video found)
/// </summary>
/// <param name="contentUrl"></param>
/// <returns></returns>
private async Task <List <string> > GenerateGeneralVideoLink(string contentUrl)
{
// BGetCore library related stuff
var videoInfoCrawler = new VideoInfoCrawler();
var videoInfo = await videoInfoCrawler.GetVideoInfo(contentUrl);
var videoUrlGrabber = new VideoUrlCrawler();
var videoUrl = await videoUrlGrabber.GetUrlBySingleContentId(videoInfo);
var urlList = new List <string>();
// Just a practice of LINQ...
if (Settings.Default.PreferFlv)
{
videoUrl.Durl.ForEach(url => urlList.Add(url.Url));
}
else
{
urlList.AddRange(
videoUrl.Durl.Where(url => url.BackupUrl != null && url.BackupUrl.Url.Count != 0)
.SelectMany(url => url.BackupUrl.Url));
}
return(urlList);
}
private static void Main(string[] args)
{
Console.Write("[INFO] Enter your video ID, e.g. av349183: ");
var inputVideo = Console.ReadLine();
Console.WriteLine("[INFO] Please wait...");
var videoInfoCrawler = new VideoInfoCrawler();
var videoInfo = videoInfoCrawler.GetVideoInfo(inputVideo).Result;
var cid = videoInfo.ContentId;
Console.WriteLine("[DEBUG] CID is " + cid);
Console.WriteLine("[INFO] Title: " + videoInfo.Title);
Console.WriteLine("[INFO] Author: " + videoInfo.Author);
Console.WriteLine("[INFO] Description: " + videoInfo.Description + "\n\n\n");
var videoUrlGrabber = new VideoUrlCrawler();
var videoUrl = videoUrlGrabber.GetUrlBySingleContentId(videoInfo).Result;
Console.WriteLine("[INFO] Got {0} video sections.", videoUrl.Durl.Count);
foreach (var url in videoUrl.Durl)
{
Console.WriteLine("[INFO] Flash video URL: {0}", url.Url);
if (url.BackupUrl != null && url.BackupUrl.Url.Count != 0)
{
foreach (var mp4Url in url.BackupUrl.Url)
{
Console.WriteLine("[INFO] MP4 backup video URL: {0}", mp4Url);
}
}
}
Console.Read();
}
public async Task <List <VideoInfo> > GetAllVideoInfoByKeyword(string keyword, bool deepSearch = false)
{
// Set initial page from page 1
var pageCount = 1;
var videoInfoList = new List <VideoInfo>();
var searchResult = await SearchByKeyword(keyword, SearchType.Video, pageCount);
// "Iterate" the pages
while (searchResult.IsSuccessful)
{
// Parse HTML content
var htmlDoc = new HtmlDocument();
htmlDoc.LoadHtml(searchResult.RawHtml);
// Get Video URLs and titles
var videoTitleAndUrlNodes = htmlDoc.DocumentNode.SelectNodes("//a[@class=\"title\"]");
// Deep search will (wayyyyyyy much) slower the fetching speed, so it's not recommend unless tag is required.
if (deepSearch)
{
var videoInfoCrawler = new VideoInfoCrawler();
// The URL does not have its initial "https:", instead it starts with "//www.bilibili.com".
// As a result, append a "https:" before it before further crawling.
foreach (var singleNode in videoTitleAndUrlNodes)
{
var url = string.Format("https:{0}", singleNode.Attributes["href"].Value);
videoInfoList.Add(await videoInfoCrawler.GetVideoInfo(url));
}
}
else
{
// Get video descriptions
var videoDescriptionNodes = htmlDoc.DocumentNode.SelectNodes("//div[@class=\"des hide\"]");
// Get video uploaders
var videoUploaderNodes = htmlDoc.DocumentNode.SelectNodes("//a[@class=\"up-name\"]");
// Iterate all video info from result (without tags)
videoInfoList.AddRange(videoDescriptionNodes.Select((t, videoCountIndex) => new VideoInfo
{
// Extract author ID from URL
Author = Regex.Match(videoUploaderNodes[videoCountIndex].Attributes["href"].Value,
@"\/(\d+)\?").Groups[1].Value,
// Extract description, new lines and tabs are removed
Description = Regex.Match(t.InnerText, "[^\t|\n|\r]+").Value,
// Extract video URL
VideoPage = string.Format("https:{0}",
videoTitleAndUrlNodes[videoCountIndex].Attributes["href"].Value),
// Extract video ID
ContentId = Regex.Match(videoTitleAndUrlNodes[videoCountIndex].Attributes["href"].Value,
@"\/av(\d+)\?").Groups[1].Value,
// Extract title
Title = videoTitleAndUrlNodes[videoCountIndex].Attributes["title"].Value
}));
}
// Update page count and move to next page...
searchResult = await SearchByKeyword(keyword, SearchType.Video, ++pageCount);
}
return(videoInfoList);
}