diff options
Diffstat (limited to 'plugins')
| -rwxr-xr-x | plugins/mangakatana.py | 2 | ||||
| -rwxr-xr-x | plugins/manganelo.py | 78 |
2 files changed, 50 insertions, 30 deletions
diff --git a/plugins/mangakatana.py b/plugins/mangakatana.py index 85fd8d0..586c4ee 100755 --- a/plugins/mangakatana.py +++ b/plugins/mangakatana.py @@ -110,7 +110,7 @@ def get_javascript_string_arrays(js_source): return arrays arr = js_source[start:end].replace("'", "").split(",") - arrays.extend(list(filter(None, arr))) + arrays.extend(list(filter(lambda x: x is not None and ".com" in x, arr))) start = end + 1 def uniq_str_arr(arr): diff --git a/plugins/manganelo.py b/plugins/manganelo.py index 5593fd4..0391eec 100755 --- a/plugins/manganelo.py +++ b/plugins/manganelo.py @@ -9,7 +9,8 @@ import json from lxml import etree headers = { - 'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36" + 'User-Agent': "Mozilla/5.0 (X11; Linux x86_64; rv:136.0) Gecko/20100101 Firefox/136.0", + 'Referer': "https://www.nelomanga.com/" } def usage(): @@ -36,18 +37,15 @@ if len(sys.argv) < 2: def download_file(url, save_path): file_size = 0 - headers = { - "accept-language": "en-US,en;q=0.9", - "accept": "image/webp,image/apng,image/*,*/*;q=0.8", - "sec-fetch-site": "cross-site", - "sec-fetch-mode": "no-cors", - "sec-fetch-dest": "image", - "referer": "https://manganelo.com/", - "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36" - } - #cookies = { - # "content_server": "server2" - #} + # headers = { + # "accept-language": "en-US,en;q=0.9", + # "accept": "image/webp,image/apng,image/*,*/*;q=0.8", + # "sec-fetch-site": "cross-site", + # "sec-fetch-mode": "no-cors", + # "sec-fetch-dest": "image", + # "referer": "https://manganelo.com/", + # "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36" + # } with requests.get(url, stream=True, headers=headers, timeout=30) as response: if not response.ok: return 0 @@ -102,7 +100,11 @@ def redirect_migrated_url(url, tree, is_chapter): return tree def list_chapters(url, chapter_list_input): + url = url.replace("mangakakalot", "manganelo").replace("manganelo", "nelomanga") response = requests.get(url, timeout=30, headers=headers) + if not response.ok: + url = url.replace("_", "-") + response = requests.get(url, timeout=30, headers=headers) response.raise_for_status() seen_titles = set() @@ -115,7 +117,7 @@ def list_chapters(url, chapter_list_input): for item in chapter_list_input: chapter_url = item.get("url") if chapter_url and len(chapter_url) > 0: - seen_urls.add(chapter_url.replace("mangakakalot", "manganelo")) + seen_urls.add(chapter_url.replace("mangakakalot", "manganelo").replace("manganelo", "nelomanga")) tree = etree.HTML(response.text) tree = redirect_migrated_url(url, tree, False) @@ -138,19 +140,25 @@ def list_chapters(url, chapter_list_input): print(json.dumps(chapters)) -def download_chapter(url, download_dir): - response = requests.get(url, timeout=30) - response.raise_for_status() +def download_chapter_images(url, download_dir, use_backup_server): + url = url.replace("mangakakalot", "manganelo").replace("manganelo", "nelomanga") + cookies = {} + try: + new_headers = headers.copy() + new_headers['referer'] = url + response = requests.get('https://nelomanga.com/change_content_s2' if use_backup_server else 'https://nelomanga.com/change_content_s1', headers=new_headers, allow_redirects=False) + response.raise_for_status() + cookies = response.cookies + except requests.HTTPError: + return False - in_progress_filepath = os.path.join(download_dir, ".in_progress") - with open(in_progress_filepath, "w") as file: - file.write(url) + response = requests.get(url, timeout=30, headers=headers, cookies=cookies) + response.raise_for_status() tree = etree.HTML(response.text) tree = redirect_migrated_url(url, tree, True) if tree is None: - os.remove(in_progress_filepath) - exit(2) + return False img_number = 1 for image_source in tree.xpath('//div[@class="container-chapter-reader"]/img/@src'): @@ -159,16 +167,26 @@ def download_chapter(url, download_dir): image_path = os.path.join(download_dir, image_name) print("Downloading {} to {}".format(image_source, image_path)) file_size = download_file(image_source, image_path) - if file_size < 255: + if file_size < 100: print("resource temporary unavailable: %s" % image_source) - os.remove(in_progress_filepath) - exit(2) + return False img_number += 1 if img_number == 1: print("Failed to find images for chapter") - os.remove(in_progress_filepath) - exit(2) + return False + + return True + +def download_chapter(url, download_dir): + in_progress_filepath = os.path.join(download_dir, ".in_progress") + with open(in_progress_filepath, "w") as file: + file.write(url) + + if not download_chapter_images(url, download_dir, False): + if not download_chapter_images(url, download_dir, True): + os.remove(in_progress_filepath) + exit(2) with open(os.path.join(download_dir, ".finished"), "w") as file: file.write("1") @@ -180,7 +198,8 @@ if command == "list": if len(sys.argv) < 3: usage_list() - url = sys.argv[2].replace("mangakakalot", "manganelo") + #url = sys.argv[2].replace("mangakakalot", "manganelo") + url = sys.argv[2] chapter_list_input = sys.stdin.read() if len(chapter_list_input) == 0: chapter_list_input = [] @@ -191,7 +210,8 @@ elif command == "download": if len(sys.argv) < 4: usage_download() - url = sys.argv[2].replace("mangakakalot", "manganelo") + #url = sys.argv[2].replace("mangakakalot", "manganelo") + url = sys.argv[2] download_dir = sys.argv[3] download_chapter(url, download_dir) else: |