use text.urljoin()

gallery_dl/cloudflare.py

@@ -41,7 +41,7 @@ def solve_challenge(session, response):
     params["jschl_answer"] = solve_jschl(response.url, page)
 
     time.sleep(4)
-    url = urllib.parse.urljoin(response.url, "/cdn-cgi/l/chk_jschl")
+    url = text.urljoin(response.url, "/cdn-cgi/l/chk_jschl")
     return session.get(url, params=params)
 
 

gallery_dl/extractor/booru.py

@@ -10,7 +10,6 @@
 
 from .common import SharedConfigExtractor, Message
 from .. import text
-from urllib.parse import urljoin
 from xml.etree import ElementTree
 import datetime
 import operator
@@ -52,7 +51,7 @@ class BooruExtractor(SharedConfigExtractor):
                 try:
                     url = image["file_url"]
                     if url.startswith("/"):
-                        url = urljoin(self.api_url, url)
+                        url = text.urljoin(self.api_url, url)
                     image.update(data)
                     yield Message.Url, url, text.nameext_from_url(url, image)
                 except KeyError:

gallery_dl/extractor/hbrowse.py

@@ -10,7 +10,6 @@
 
 from .common import ChapterExtractor, MangaExtractor
 from .. import text
-from urllib.parse import urljoin
 import json
 
 
@@ -61,7 +60,7 @@ class HbrowseMangaExtractor(HbrowseExtractor, MangaExtractor):
             title, pos = text.extract(page, '>View ', '<', pos)
             data["chapter"] = text.parse_int(url.rpartition("/")[2][1:])
             data["title"] = title
-            results.append((urljoin(self.root, url), data.copy()))
+            results.append((text.urljoin(self.root, url), data.copy()))
 
 
 class HbrowseChapterExtractor(HbrowseExtractor, ChapterExtractor):

gallery_dl/extractor/hentaifoundry.py

@@ -10,7 +10,6 @@
 
 from .common import Extractor, Message
 from .. import text, util, exception
-from urllib.parse import urljoin
 
 
 class HentaifoundryExtractor(Extractor):
@@ -47,7 +46,7 @@ class HentaifoundryExtractor(Extractor):
 
     def get_image_metadata(self, url):
         """Collect metadata for an image"""
-        page = self.request(urljoin(self.root, url)).text
+        page = self.request(text.urljoin(self.root, url)).text
         index = url.rsplit("/", 2)[1]
         title, pos = text.extract(
             page, 'Pictures</a> &raquo; <span>', '<')

gallery_dl/extractor/imagehosts.py

@@ -12,7 +12,6 @@ from .common import Extractor, Message
 from .. import text, exception
 from ..cache import memcache
 from os.path import splitext
-from urllib.parse import urljoin
 
 
 class ImagehostImageExtractor(Extractor):
@@ -142,8 +141,7 @@ class ImagevenueImageExtractor(ImagehostImageExtractor):
 
     def get_info(self, page):
         url = text.extract(page, 'SRC="', '"')[0]
-        url = urljoin(self.url, url)
+        return text.urljoin(self.url, url), url
-        return url, url
 
 
 class ImagetwistImageExtractor(ImagehostImageExtractor):

gallery_dl/extractor/khinsider.py

@@ -10,7 +10,6 @@
 
 from .common import AsynchronousExtractor, Message
 from .. import text, exception
-from urllib.parse import urljoin
 
 
 class KhinsiderSoundtrackExtractor(AsynchronousExtractor):
@@ -63,7 +62,8 @@ class KhinsiderSoundtrackExtractor(AsynchronousExtractor):
         page = text.extract(page, '<table id="songlist">', '</table>')[0]
         for num, url in enumerate(text.extract_iter(
                 page, '<td class="clickable-row"><a href="', '"'), 1):
-            page = self.request(urljoin(self.root, url), encoding="utf-8").text
+            url = text.urljoin(self.root, url)
+            page = self.request(url, encoding="utf-8").text
             url = text.extract(
                 page, '<p><a style="color: #21363f;" href="', '"')[0]
             yield url, text.nameext_from_url(url, {"num": num})

gallery_dl/extractor/mangadex.py

@@ -10,7 +10,6 @@
 
 from .common import ChapterExtractor, MangaExtractor
 from .. import text, util, exception
-from urllib.parse import urljoin
 import json
 import re
 
@@ -84,7 +83,7 @@ class MangadexChapterExtractor(MangadexExtractor, ChapterExtractor):
         pagelist, pos = text.extract(page, "var page_array = [", "]", pos)
         server  , pos = text.extract(page, "var server = '", "'", pos)
 
-        base = urljoin(self.root, server + dataurl + "/")
+        base = text.urljoin(self.root, server + dataurl + "/")
 
         return [
             (base + page, None)

gallery_dl/extractor/mangahere.py

@@ -10,7 +10,6 @@
 
 from .common import ChapterExtractor, MangaExtractor
 from .. import text
-from urllib.parse import urljoin
 import re
 
 
@@ -51,7 +50,7 @@ class MangahereMangaExtractor(MangaExtractor):
             volume, pos = text.extract(page, 'span class="mr6">', '<', pos)
             title, pos = text.extract(page, '/span>', '<', pos)
             date, pos = text.extract(page, 'class="right">', '</span>', pos)
-            results.append((urljoin("http:", url), {
+            results.append((text.urljoin("http:", url), {
                 "manga": manga, "title": title, "date": date,
                 "volume": text.parse_int(volume.rpartition(" ")[2]),
                 "chapter": text.parse_int(chapter),

gallery_dl/extractor/mangapark.py

@@ -10,7 +10,6 @@
 
 from .common import ChapterExtractor, MangaExtractor
 from .. import text
-from urllib.parse import urljoin
 
 
 class MangaparkExtractor():
@@ -120,7 +119,7 @@ class MangaparkChapterExtractor(MangaparkExtractor, ChapterExtractor):
             num += 1
             width , pos = text.extract(page, ' width="', '"', pos)
             height, pos = text.extract(page, ' _heighth="', '"', pos)
-            yield urljoin(self.root, url), {
+            yield text.urljoin(self.root, url), {
                 "page": num,
                 "width": width,
                 "height": height,

gallery_dl/extractor/mangastream.py

@@ -10,7 +10,6 @@
 
 from .common import ChapterExtractor
 from .. import text
-from urllib.parse import urljoin
 
 
 class MangastreamChapterExtractor(ChapterExtractor):
@@ -47,5 +46,5 @@ class MangastreamChapterExtractor(ChapterExtractor):
             pos = page.index(' class="page"')
             next_url = text.extract(page, ' href="', '"', pos)[0]
             image_url = text.extract(page, ' src="', '"', pos)[0]
-            yield urljoin(self.base_url, image_url), None
+            yield text.urljoin(self.base_url, image_url), None
-            page = self.request(urljoin(self.base_url, next_url)).text
+            page = self.request(text.urljoin(self.base_url, next_url)).text