Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-25 12:12:34 +01:00
Code Issues Releases Wiki Activity

[exhentai] catch more error states (#356, #360)

Browse Source 
- warn on MPV-enabled galleries
- catch parsing errors for gallery pages and image info
- write page content to debug output
This commit is contained in:
Mike Fährmann 2019-07-29 16:54:31 +02:00
parent a90280f4e7
commit 81b35ed3cb
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 29 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
gallery_dl/extractor/exhentai.py
View File

@ -136,6 +136,14 @@ class ExhentaiGalleryExtractor(ExhentaiExtractor):
if self.gallery_token:
gpage = self._gallery_page()
self.image_token = text.extract(gpage, 'hentai.org/s/', '"')[0]
if "hentai.org/mpv/" in gpage:
self.log.warning("Extraction with Multi-Page Viewer "
"enabled is not supported")
if not self.image_token:
self.log.error("Failed to extract image token "
"from gallery page")
self.log.debug("Page content:\n%s", gpage)
return
self.wait()
ipage = self._image_page()
else:
@ -201,12 +209,16 @@ class ExhentaiGalleryExtractor(ExhentaiExtractor):
iurl = extr('<img id="img" src="', '"')
orig = extr('hentai.org/fullimg.php', '"')
if self.original and orig:
url = self.root + "/fullimg.php" + text.unescape(orig)
data = self._parse_original_info(extr('ownload original', '<'))
else:
url = iurl
data = self._parse_image_info(url)
try:
if self.original and orig:
url = self.root + "/fullimg.php" + text.unescape(orig)
data = self._parse_original_info(extr('ownload original', '<'))
else:
url = iurl
data = self._parse_image_info(url)
except IndexError:
self.log.warning("Unable to parse image info for '%s'", url)
self.log.debug("Page content:\n%s", page)
data["num"] = self.image_num
data["image_token"] = self.key["start"] = extr('var startkey="', '";')
@ -232,13 +244,17 @@ class ExhentaiGalleryExtractor(ExhentaiExtractor):
imgurl , pos = text.extract(page["i3"], 'id="img" src="', '"', pos)
origurl, pos = text.extract(page["i7"], '<a href="', '"')
if self.original and origurl:
url = text.unescape(origurl)
data = self._parse_original_info(
text.extract(page["i7"], "ownload original", "<", pos)[0])
else:
url = imgurl
data = self._parse_image_info(url)
try:
if self.original and origurl:
url = text.unescape(origurl)
data = self._parse_original_info(text.extract(
page["i7"], "ownload original", "<", pos)[0])
else:
url = imgurl
data = self._parse_image_info(url)
except IndexError:
self.log.warning("Unable to parse image info for '%s'", url)
self.log.debug("Page content:\n%s", page)
data["num"] = request["page"]
data["image_token"] = imgkey