1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
#!/usr/bin/env python3
import os
import time
import sys
import requests
import json
import re
from lxml import etree
def usage():
print("mangadex.py command")
print("commands:")
print(" download")
print(" list")
exit(1)
def usage_list():
print("mangadex.py list <url>")
exit(1)
def usage_download():
print("mangadex.py download <url> <download_dir>")
print("examples:")
print(" mangadex.py download \"https://mangadex.org/title/7139/one-punch-man\" /home/adam/Manga/MangaName")
print("")
print("Note: The manga directory has to exist.")
exit(1)
if len(sys.argv) < 2:
usage()
def download_file(url, save_path):
with requests.get(url, stream=True) as response:
if not response.ok:
return False
with open(save_path, "wb") as file:
for chunk in response.iter_content(chunk_size=8192):
if chunk:
file.write(chunk)
return True
def title_url_extract_manga_id(url):
result = re.search("mangadex.org/title/([0-9]+)/", url)
if result and len(result.groups()) > 0:
return result.groups()[0]
# TODO: Support pagination. Currently only the n latest chapters are listed,
# but going through all pages might be too slow for large manga like naruto
def list_chapters(url, chapter_list_input):
manga_id = title_url_extract_manga_id(url)
if not manga_id:
print("Failed to extract manga id from url: %s. Note: url is expected to be in this format: mangadex.org/title/<number>/..." % url)
exit(2)
response = requests.get(url)
if response.status_code != 200:
print("Failed to list chapters, server responded with status code %d" % response.status_code)
exit(2)
seen_titles = set()
for item in chapter_list_input:
title = item.get("title")
if title and len(title) > 0:
seen_titles.add(title.lower().replace(" ", ""))
seen_urls = set()
for item in chapter_list_input:
url = item.get("url")
if url and len(url) > 0:
seen_urls.add(url)
lang = "1" # english
tree = etree.HTML(response.text)
chapters = []
prev_chapter_number = None
for element in tree.xpath("//div[@data-manga-id='%s']" % manga_id):
chapter_lang = element.attrib.get("data-lang")
if chapter_lang != lang:
continue
chapter_id = element.attrib.get("data-id")
chapter_url = "https://mangadex.org/chapter/%s" % chapter_id
chapter_title = element.attrib.get("data-title") # optional
chapter_number = element.attrib.get("data-chapter")
if prev_chapter_number and chapter_number == prev_chapter_number:
continue
prev_chapter_number = chapter_number
chapter_name = "Ch. %s" % chapter_number
if chapter_title:
chapter_name += " - %s" % chapter_title
if chapter_title.lower().replace(" ", "") in seen_titles or chapter_url in seen_urls:
break
chapters.append({ "name": chapter_name, "url": chapter_url })
print(json.dumps(chapters))
def chapter_url_extract_manga_id(url):
result = re.search("mangadex.org/chapter/([0-9]+)", url)
if result and len(result.groups()) > 0:
return result.groups()[0]
def download_chapter(url, download_dir):
request_url = url
manga_id = chapter_url_extract_manga_id(url)
if not manga_id:
print("Failed to extract manga id from url: %s. Note: url is expected to be in this format: mangadex.org/chapter/<number>" % url)
exit(2)
url = "https://mangadex.org/api/?id=%s&server=null&type=chapter" % manga_id
response = requests.get(url)
if response.status_code != 200:
print("Failed to list chapter images, server responded with status code %d" % response.status_code)
exit(2)
in_progress_filepath = os.path.join(download_dir, ".in_progress")
with open(in_progress_filepath, "w") as file:
file.write(request_url)
img_number = 1
json_response = response.json()
status = json_response["status"]
if status != "OK":
print("Expected server response OK, got %s" % status)
exit(2)
chapter_hash = json_response["hash"]
for image_name in json_response["page_array"]:
image_url = "https://mangadex.org/data/%s/%s" % (chapter_hash, image_name)
ext = image_url[image_url.rfind("."):]
image_name = str(img_number) + ext
image_path = os.path.join(download_dir, image_name)
print("Downloading {} to {}".format(image_url, image_path))
if not download_file(image_url, image_path):
print("Failed to download image: %s" % image_url)
os.remove(in_progress_filepath)
exit(2)
img_number += 1
if img_number == 1:
print("Failed to find images for chapter")
os.remove(in_progress_filepath)
exit(2)
with open(os.path.join(download_dir, ".finished"), "w") as file:
file.write("1")
os.remove(in_progress_filepath)
command = sys.argv[1]
if command == "list":
if len(sys.argv) < 3:
usage_list()
url = sys.argv[2]
chapter_list_input = sys.stdin.read()
if len(chapter_list_input) == 0:
chapter_list_input = []
else:
chapter_list_input = json.loads(chapter_list_input)
list_chapters(url, chapter_list_input)
elif command == "download":
if len(sys.argv) < 4:
usage_download()
url = sys.argv[2]
download_dir = sys.argv[3]
download_chapter(url, download_dir)
else:
usage()
|
