Пример #1
0
        private async Task GetChapterAsync(string line)
        {
            if (line == "")
            {
                return;
            }
            chapterLinks.RemoveRange(0, chapterLinks.Count);
            int urlEnd = (line.IndexOf('&') == -1) ? line.Length : line.IndexOf('&');

            using (WebClient client = new WebClient())
            {
                int    i = 0;
                string firstLink = "Thanks for looking through my source code lol";
                bool   checkedForLink, foundEnd = false;
                while (true)
                {
                    i++;
                    string html = await client.DownloadStringTaskAsync(line.Substring(0, urlEnd) + "&page=" + i);

                    var doc = new HtmlAgilityPack.HtmlDocument();   //HtmlAgility magic
                    doc.LoadHtml(html);
                    var div = doc.GetElementbyId("_listUl");
                    HtmlNodeCollection childNodes = div.ChildNodes;
                    checkedForLink = false;
                    for (int j = 0; j < childNodes.Count; j++)
                    {
                        if (childNodes[j].HasChildNodes)
                        {
                            if (!checkedForLink && firstLink != childNodes[j].ChildNodes[1].Attributes["href"].Value)   //stop if no higher page count could be found
                            {
                                firstLink      = childNodes[j].ChildNodes[1].Attributes["href"].Value;
                                checkedForLink = true;
                            }
                            else if (!checkedForLink)
                            {
                                foundEnd = true; break;
                            }
                            chapterLinks.Add(childNodes[j].ChildNodes[1].Attributes["href"].Value);              //link of the chapter
                            chapterNames.Add(childNodes[j].ChildNodes[1].ChildNodes[3].ChildNodes[0].InnerHtml); //name of the chapter
                        }
                    }
                    if (foundEnd)
                    {
                        break;
                    }
                }
            }
            chapterLinks.Reverse();
            absoluteChapterNR += chapterLinks.Count;
            // add all chapter links and the chapter names of the just scrapped site to the full list of the comic
            string[] tempChapterLinks = new string[chapterLinks.Count];
            for (int i = 0; i < chapterLinks.Count; i++)
            {
                tempChapterLinks[i] = chapterLinks[i];
            }
            ToonChapters.Add(tempChapterLinks);
            chapterNames.Reverse();
            string[] tempChapterNames = new string[chapterNames.Count];
            for (int i = 0; i < chapterNames.Count; i++)
            {
                tempChapterNames[i] = chapterNames[i];
            }
            ToonChapterNames.Add(tempChapterNames);
        }
Пример #2
0
        private async Task GetChapterAsync(string line)
        {
            if (line == "")
            {
                return;
            }
            chapterLinks.RemoveRange(0, chapterLinks.Count);
            int urlEnd = (line.IndexOf('&') == -1) ? line.Length : line.IndexOf('&');

            using (WebClient client = new WebClient())
            {
                int    i = 0;
                string firstLink = "Thanks for looking through my source code lol";
                bool   checkedForLink, foundEnd = false;
                while (true)
                {
                    i++;
                    processInfo.Invoke((MethodInvoker) delegate { processInfo.Text = $"scoping tab {i}"; }); //run on the UI thread
                    client.Headers.Add("Cookie", "pagGDPR=true;");                                           //add cookies to bypass age verification
                    IWebProxy proxy = WebRequest.DefaultWebProxy;                                            //add default proxy
                    client.Proxy = proxy;
                    string html = await client.DownloadStringTaskAsync(line.Substring(0, urlEnd) + "&page=" + i);

                    HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();   //HtmlAgility magic
                    doc.LoadHtml(html);
                    HtmlNode           div        = doc.GetElementbyId("_listUl");
                    HtmlNodeCollection childNodes = div.ChildNodes;
                    checkedForLink = false;
                    for (int j = 0; j < childNodes.Count; j++)
                    {
                        if (childNodes[j].HasChildNodes)
                        {
                            if (!checkedForLink && firstLink != childNodes[j].ChildNodes[1].Attributes["href"].Value)   //stop if no higher page count could be found
                            {
                                firstLink      = childNodes[j].ChildNodes[1].Attributes["href"].Value;
                                checkedForLink = true;
                            }
                            else if (!checkedForLink)
                            {
                                foundEnd = true; break;
                            }
                            chapterLinks.Add(childNodes[j].ChildNodes[1].Attributes["href"].Value);              //link of the chapter
                            chapterNames.Add(childNodes[j].ChildNodes[1].ChildNodes[3].ChildNodes[0].InnerHtml); //name of the chapter
                        }
                    }
                    if (foundEnd)
                    {
                        break;
                    }
                }
            }
            chapterLinks.Reverse();
            absoluteChapterNR += chapterLinks.Count;
            // add all chapter links and the chapter names of the just scrapped site to the full list of the comic
            string[] tempChapterLinks = new string[chapterLinks.Count];
            for (int i = 0; i < chapterLinks.Count; i++)
            {
                tempChapterLinks[i] = chapterLinks[i];
            }
            ToonChapters.Add(tempChapterLinks);
            chapterNames.Reverse();
            string[] tempChapterNames = new string[chapterNames.Count];
            //sanitize the names of chapters!
            string invalidChars = new string(Path.GetInvalidFileNameChars()) + new string(Path.GetInvalidPathChars());

            for (int i = 0; i < chapterNames.Count; i++)
            {
                foreach (char c in invalidChars)
                {
                    chapterNames[i] = chapterNames[i].Replace(c.ToString(), "");
                }
                tempChapterNames[i] = chapterNames[i];
            }
            ToonChapterNames.Add(tempChapterNames);
        }