^q^

Author: KurtBestor

README.md

@@ -10,7 +10,7 @@
 ## Links
 - [Download](https://github.com/KurtBestor/Hitomi-Downloader/releases/latest)
 - [Issues](https://github.com/KurtBestor/Hitomi-Downloader/issues)
-- [Scripts](https://github.com/KurtBestor/Hitomi-Downloader/wiki/Scripts)
+- [Scripts & Plugins](https://github.com/KurtBestor/Hitomi-Downloader/wiki/Scripts-&-Plugins)
 - [Chrome Extension](https://github.com/KurtBestor/Hitomi-Downloader/wiki/Chrome-Extension)
 
 ## Demo
@@ -60,8 +60,9 @@
 | **Iwara** | <https://iwara.tv><br><https://ecchi.iwara.tv> |
 | **Jmana** | <https://jmana.net> |
 | **カクヨム** | <https://kakuyomu.jp> |
-| **Likee** | <https://likee.video> |
 | **Luscious** | <https://luscious.net> |
+| **Mastodon** | <https://mastodon.social> |
+| **Misskey** | <https://misskey.io> |
 | **MyReadingManga** | <https://myreadingmanga.info> |
 | **Naver Blog** | <https://blog.naver.com> |
 | **Naver Cafe** | <https://cafe.naver.com> |
@@ -82,6 +83,7 @@
 | **Sankaku Complex** | <https://www.sankakucomplex.com><br><https://chan.sankakucomplex.com><br><https://idol.sankakucomplex.com> |
 | **Soundcloud** | <https://soundcloud.com> |
 | **小説家になろう** | <https://syosetu.com> |
+| **TikTok** | <https://tiktok.com><br><https://douyin.com>|
 | **TOKYO Motion** | <https://tokyomotion.net> |
 | **Tumblr** | <https://tumblr.com> |
 | **Twitch** | <https://twitch.tv> |

src/extractor/afreeca_downloader.py

@@ -22,6 +22,11 @@ def __init__(self, stream, referer, id, title, url_thumb):
         downloader.download(url_thumb, buffer=self.thumb)
 
 
+class LoginRequired(errors.LoginRequired):
+    def __init__(self, *args):
+        super().__init__(*args, method='browser', url='https://login.afreecatv.com/afreeca/login.php')
+
+
 
 class Downloader_afreeca(Downloader):
     type = 'afreeca'
@@ -61,11 +66,11 @@ def get_video(url, session, cw):
 
     html = downloader.read_html(url, session=session)
     if "document.location.href='https://login." in html:
-        raise errors.LoginRequired()
+        raise LoginRequired()
     if len(html) < 2000:
         alert = re.find(r'''alert\(['"](.+?)['"]\)''', html)
         if alert:
-            raise errors.LoginRequired(alert)
+            raise LoginRequired(alert)
     soup = Soup(html)
 
     url_thumb = soup.find('meta', {'property': 'og:image'}).attrs['content']
@@ -85,7 +90,7 @@ def get_video(url, session, cw):
     title = data['full_title']
 
     if data.get('adult_status') == 'notLogin':
-        raise errors.LoginRequired(title)
+        raise LoginRequired(title)
 
     urls_m3u8 = []
     for file in data['files']:

src/extractor/baraag_downloader.py

@@ -28,7 +28,6 @@ def read(self):
         id_ = get_id(self.url)
         info = get_info('baraag.net', id_, f'baraag_{id_}', self.session, self.cw)
 
-        for img in info['imgs']:
-            self.urls.append(img.url)
+        self.urls += info['files']
 
         self.title = clean_title('{} (baraag_{})'.format(info['title'], id_))

src/extractor/etc_downloader.py

@@ -120,7 +120,7 @@ def _get_video(url, session, cw, ie_key=None, allow_m3u8=True):
     fs = []
     for i, f in enumerate(formats):
         f['_index'] = i
-        f['_resolution'] = int_or_none(re.find('([0-9]+)p', f['format'], re.IGNORECASE)) or f.get('height') or f.get('width') or int_or_none(f.get('quality')) or int(f.get('vcodec', 'none') != 'none') #5995
+        f['_resolution'] = int_or_none(re.find(r'([0-9]+)p', f['format'], re.I)) or f.get('height') or f.get('width') or int_or_none(f.get('quality')) or int(f.get('vcodec', 'none') != 'none') #5995
         f['_vbr'] = f.get('vbr') or 0
         f['_audio'] = f.get('abr') or f.get('asr') or int(f.get('acodec', 'none') != 'none')
         print_(format_(f))
@@ -144,7 +144,7 @@ def filter_f(fs):
             print_('invalid url: {}'.format(f['url']))
         return list(fs)[0]#
 
-    f_video = filter_f(reversed(sorted(fs, key=lambda f:(f['_resolution'], f['_vbr'], f['_index']))))
+    f_video = filter_f(sorted(fs, key=lambda f:(f['_resolution'], int(bool(f['_audio'])), f['_vbr'], f['_index']), reverse=True)) #6072, #6118
     print_('video0: {}'.format(format_(f_video)))
 
     if f_video['_audio']:

src/extractor/fc2_downloader.py

@@ -14,8 +14,8 @@ class Downloader_fc2(Downloader):
 
     @classmethod
     def fix_url(cls, url):
-        if not re.match('https?://.+', url, re.IGNORECASE):
-            url = 'https://video.fc2.com/content/{}'.format(url)
+        if not re.match(r'https?://.+', url, re.I):
+            url = f'https://video.fc2.com/content/{url}'
         return url
 
     @classmethod

src/extractor/iwara_downloader.py

@@ -126,7 +126,7 @@ def f(html, browser=None):
         if time() - t0 > 10 or '/profile/' in url.lower():
             for a in soup.findAll('a'):
                 if urljoin(url, a.get('href', '')) == urljoin(url, '/login'):
-                    raise errors.LoginRequired(method='browser', url='https://www.iwara.tv/login') #5794
+                    raise errors.LoginRequired(method='browser', url='https://www.iwara.tv/login', cookie=False) #5794
         buttons = soup.findAll(class_='button--primary')
         if buttons:
             for i, button in enumerate(buttons):

src/extractor/jmana_downloader.py

@@ -9,7 +9,7 @@
 import bs4
 import clf2
 PATTERN = r'jmana[0-9]*.*/(comic_list_title|book)\?book'
-PATTERN_ALL = r'jmana[0-9]*.*/(comic_list_title|book|bookdetail)\?book'
+PATTERN_ALL = r'jmana[0-9]*.*/((comic_list_title|book|bookdetail)\?book|book_by_title\?title)' #6157
 PATTERN_ID = '[?&]bookdetailid=([0-9]+)'
 
 
@@ -56,7 +56,7 @@ def init(self):
             self.url = self.fix_url(url)
             self._soup = None
 
-            for i, page in enumerate(get_pages(self.url, self.session, self.soup)):
+            for i, page in enumerate(get_pages(self.url, self.soup, self.session)):
                 if page.id == int(op['value']):
                     break
             else:
@@ -147,10 +147,7 @@ def get_imgs_page(page, referer, session, cw=None):
     return imgs
 
 
-def get_pages(url, session=None, soup=None):
-    if soup is None:
-        res = clf2.solve(url, session=session) #4070
-        soup = Soup(res['html'])
+def get_pages(url, soup, session):
     pages = []
     for inner in soup.findAll('div', class_='inner'):
         a = inner.find('a')
@@ -172,12 +169,13 @@ def get_pages(url, session=None, soup=None):
 
 
 @page_selector.register('jmana')
-@try_n(4)
-def f(url):
+def f(url, win):
     if re.search(PATTERN_ID, url):
         raise Exception(tr_('목록 주소를 입력해주세요'))
     session = Session()
-    pages = get_pages(url, session=session)
+    res = clf2.solve(url, session=session, win=win) #4070
+    soup = Soup(res['html'])
+    pages = get_pages(url, soup, session)
     return pages
 
 
@@ -186,7 +184,7 @@ def get_imgs(url, title, session, soup=None, cw=None):
     if soup is None:
         html = downloader.read_html(url, session=session)
         soup = Soup(html)
-    pages = get_pages(url, soup=soup)
+    pages = get_pages(url, soup, session)
     print_('pages: {}'.format(len(pages)))
     pages = page_selector.filter(pages, cw)
     imgs = []

src/extractor/lhscan_downloader.py

@@ -36,10 +36,10 @@ def __init__(self, title, url):
         self.url = url
 
 
-def get_soup_session(url, cw=None):
+def get_soup_session(url, cw=None, win=None):
     print_ = get_print(cw)
     session = Session()
-    res = clf2.solve(url, session=session, cw=cw)
+    res = clf2.solve(url, session=session, cw=cw, win=win)
     print_('{} -> {}'.format(url, res['url']))
     if res['url'].rstrip('/') == 'https://welovemanga.one':
         raise errors.LoginRequired()
@@ -55,10 +55,9 @@ class Downloader_lhscan(Downloader):
         ]
     MAX_CORE = 16
     display_name = 'LHScan'
-    _soup = None
 
     def init(self):
-        self._soup, self.session = get_soup_session(self.url, self.cw)
+        self.soup, self.session = get_soup_session(self.url, self.cw)
         if not self.soup.find('ul', class_='manga-info'):
             raise errors.Invalid('{}: {}'.format(tr_('목록 주소를 입력해주세요'), self.url))
 
@@ -68,21 +67,6 @@ def fix_url(cls, url):
         url = url.replace('welovemanga.net', 'welovemanga.one') #4298
         return url
 
-    @property
-    def soup(self):
-        if self._soup is None:
-            for try_ in range(8):
-                try:
-                    html = downloader.read_html(self.url, session=self.session)
-                    break
-                except Exception as e:
-                    e_ = e
-                    print(e)
-            else:
-                raise e_
-            self._soup = Soup(html)
-        return self._soup
-
     @property
     def name(self):
         title = self.soup.find('ul', class_='manga-info').find('h3').text
@@ -115,10 +99,10 @@ def get_imgs_page(page, referer, session, cw=None):
         pass
     soup = Soup(html)
 
-    view = soup.find('div', class_='chapter-content')
-
-    if not view:
-        raise Exception('no chapter-content')
+    cid = re.find(r'''load_image\(([0-9]+)''', html)
+    if cid: #6186
+        url_api = urljoin(page.url, f'/app/manga/controllers/cont.listImg.php?cid={cid}')
+        soup = downloader.read_soup(url_api, page.url, session=session)
 
     imgs = []
     for img in soup.findAll('img', class_='chapter-img'):
@@ -140,9 +124,12 @@ def get_imgs_page(page, referer, session, cw=None):
             continue
         if '/uploads/lazy_loading.gif' in src:
             continue
+        if '/xstaff.jpg.pagespeed.ic.gPQ2SGcYaN.webp' in src:
+            continue
         src = src.replace('\n', '').replace('\r', '') #5238
-        if 'proxy.php?link=' not in src: #5351
-            src = 'https://welovekai.com/proxy.php?link=' + src #5238
+        #6105
+##        if 'proxy.php?link=' not in src: #5351
+##            src = 'https://welovekai.com/proxy.php?link=' + src #5238
         if not imgs:
             print_(src0)
             print_(src)
@@ -174,9 +161,8 @@ def get_pages(url, session, soup=None, cw=None):
 
 
 @page_selector.register('lhscan')
-@try_n(4)
-def f(url):
-    soup, session = get_soup_session(url)
+def f(url, win):
+    soup, session = get_soup_session(url, win=win)
     pages = get_pages(url, session, soup=soup)
     return pages