def m(book):
p_green("[I] Saving in epub...")
p_green("[I] Meta and information generation...")
characters = book["characters"]
bookr = epub.EpubBook()
id_gen = "wattpad" + str(book["id"])
bookr.set_identifier(id_gen)
bookr.set_title(book["title"])
bookr.set_language(book["description"])
bookr.add_author(book["authors"])
bookr.add_item(epub.EpubNcx())
bookr.add_item(epub.EpubNav())
bookr.set_cover("cover.jpg", book["cover"])
book_spine = ['cover', 'nav']
p_green("[I] Characters generation...")
book_characters = []
count_characters = 1
for one_char in characters:
print('[{c_num}/{c_all}] Generation "{chapter_title}": {chapter_id}'.
format(c_num=str(count_characters),
c_all=str(len(characters) + 1),
chapter_title=one_char["title"],
chapter_id=one_char["id"]))
capt = chapter_gen(one_char["text"])
captr = epub.EpubHtml(title=one_char["title"],
file_name='chap_' + str(count_characters) +
'.xhtml',
lang='hr')
count_characters += 1
captr.content = capt["text"]
book_spine.append(captr)
book_characters.append(captr)
bookr.add_item(captr)
bookr.toc = (epub.Link('chap_01.xhtml', 'Introduction',
'intro'), (epub.Section('Simple book'),
tuple(book_characters)))
p_green("[I] Saving to epub...")
save_name = os.getcwd() + "/downloads/" + str(
book["id"]) + " - " + save_file.rename_valid_f(book["title"]) + ".epub"
bookr.spine = book_spine
epub.write_epub(save_name, bookr, {})
p_green("[I] Saved to epub")
def m(book):
p_green("[I] Saving in txt...")
info_book = templ_main().format(book["title"], book["authors"],
book["description"], book["source"])
save_file.save_txt_info(book["id"] + " - " + book["title"], info_book)
chapters = book["characters"]
chapter_count = 0
for capter in chapters:
chapter_count += 1
print(
'[{c_num}/{c_all}] Saving "{chapter_title}": {chapter_id}'.format(
c_num=str(chapter_count),
c_all=str(len(chapters)),
chapter_title=capter["title"],
chapter_id=capter["id"]))
chapter_text = ""
title = capter["title"]
text = capter["text"]
text = text.replace("<br>", "\n")
soup = BeautifulSoup(text, 'html5lib')
tags = soup.find_all('img', src=True)
for ii in range(len(tags)):
img_tag_url = (tags[ii])["src"]
save_file.save_url_name(
"#" + str(chapter_count) + "~" + str(ii + 1) + ".jpg",
book["id"] + " - " + book["title"], img_tag_url)
img_tag = soup.select_one("img:nth-of-type(1)")
img_tag.decompose()
tags = soup.find_all("p")
for tag in tags:
chapter_add = "\n\n" + tag.text
chapter_text += chapter_add
save_file.save_txt(book["id"] + " - " + book["title"],
"#" + str(chapter_count) + " " + title + ".txt",
templ_ch().format(capter["title"], chapter_text))
p_green("[I] Saved to txt")
def create_profile(nickname, type_save):
p_green("[I] Reading lists from " + nickname +
" are added to the queue...")
session = requests.session()
session.headers['User-Agent'] = ''
lists_url = 'https://www.wattpad.com/api/v3/users/{nickname}/lists?limit=100'
list_json = session.get(lists_url.format(nickname=nickname)).json()
count_all = list_json["total"]
list_prep = list_json["lists"]
count_one = 0
list_url_ready = []
for list_one in list_prep:
count_one += 1
print(
"[{count_one}/{count_all}] The {name} list is added to the queue : {id}"
.format(count_all=count_all,
count_one=count_one,
name=list_one["name"],
id=list_one["id"]))
list_url_ready.append("https://www.wattpad.com/list/" +
str(list_one["id"]))
for down_url in list_url_ready:
create_list(down_url, type_save)
p_green("[I] All reading lists saved")
def m(book):
p_green("[I] Saving in fb2...")
root_dir = os.getcwd()
try:
os.mkdir(root_dir + "/downloads")
except:
pass
chapters = book["characters"]
binary = ""
chapters_text = ""
chapter_count = 0
for chapter in chapters:
chapter_count += 1
print('[{c_num}/{c_all}] Generation "{chapter_title}": {chapter_id}'.
format(c_num=str(chapter_count),
c_all=str(len(chapters) + 1),
chapter_title=chapter["title"],
chapter_id=chapter["id"]))
capt = chapter_gen(chapter["text"])
chapters_text += templ_char().format(title=chapter["title"],
text=capt["text"])
binary += capt["image"]
p_green('[{c_all}/{c_all}] Meta and information generation'.format(
c_all=str(len(chapters) + 1)))
ready_book = templ().format(link=book["source"],
namebook=book["title"],
annotation=book["description"],
nickname=str(book["authors"]),
characters=chapters_text,
binarys=binary,
cover=base64_get(book["cover"]))
file = open(root_dir + "/downloads/" + str(book["id"]) + " - " +
save_file.rename_valid_f(book["title"]) + ".fb2",
"w",
encoding="utf-8")
file.write(ready_book)
file.close()
p_green("[I] Saved to fb2")
def download_story(story_id, type_save):
storyinfo = session.get(API_STORYINFO + story_id,
params={
'drafts': 1,
'include_deleted': 1
}).json()
story_title = storyinfo['title']
story_description = storyinfo['description']
story_createDate = dateutil.parser.parse(storyinfo['createDate'])
story_modifyDate = dateutil.parser.parse(storyinfo['modifyDate'])
story_author = storyinfo['user']['name']
story_categories = [
categories[c] for c in storyinfo['categories'] if c in categories
]
story_rating = storyinfo['rating'] # TODO: I think 4 is adult?
story_cover = session.get(storyinfo['cover']).content
if type_save == "txt":
save_file.save_bytes(
str(story_id) + " - " + story_title, "cover.jpg", story_cover)
story_url = storyinfo['url']
p_green('[I] Story "{story_title}": {story_id}'.format(
story_title=story_title, story_id=story_id))
book = {}
book["title"] = story_title
book["id"] = story_id
book["authors"] = story_author
book["categories"] = story_categories
book["description"] = story_description
book["url"] = story_url
book["'publisher"] = "Wattpad Downloader"
book["source"] = story_url
book["rating"] = story_rating
book["cover"] = storyinfo["cover"]
characters = []
countsp = 0
countspa = len(storyinfo["parts"])
for part in storyinfo['parts']:
countsp += 1
chapter_title = part['title']
if part['draft']:
p_red(
'[{c_num}/{c_all}] Skipping "{chapter_title}": {chapter_id}, part is draft'
.format(c_num=countsp,
c_all=countspa,
chapter_title=chapter_title,
chapter_id=chapter_id))
continue
if 'deleted' in part and part['deleted']:
p_red(
'[{c_num}/{c_all}] Skipping "{chapter_title}": {chapter_id}, part is deleted'
.format(c_num=countsp,
c_all=countspa,
chapter_title=chapter_title,
chapter_id=chapter_id))
continue
chapter_id = part['id']
chapter_modifyDate = dateutil.parser.parse(part['modifyDate'])
print('[{c_num}/{c_all}] Downloading "{chapter_title}": {chapter_id}'.
format(c_num=countsp,
c_all=countspa,
chapter_title=chapter_title,
chapter_id=chapter_id))
chapter_html = session.get(API_STORYTEXT,
params={
'id': chapter_id,
'output': 'json'
}).json()['text']
chapter_html = smartypants.smartypants(chapter_html)
section = {}
section["text"] = chapter_html
section["title"] = chapter_title
section["id"] = chapter_id
characters.append(section)
book["characters"] = characters
if type_save == "epub":
epub_create.m(book)
if type_save == "fb2":
fb2_create.m(book)
elif type_save == "txt":
txt_create.m(book)
else:
pass
def create_list(list_url, type_save):
try:
os.rename("downloads", "downloads_temp")
except:
aa = 00
sessionreq = get_session()
resp = sessionreq.get(list_url)
soup = BeautifulSoup(resp.text, 'html5lib')
storys_url = ""
count_url = 0
id_list = []
match = re.search(r'\d+', list_url)
url_id = match.group()
tags = soup.find_all("h1")
list_name = (tags[0]).text
p_green("[I] " + (tags[0]).text + " list")
tags = soup.find_all("a", href=True)
for tag in tags:
if (("on-navigate" and "story/") in str(tag)) and ("img"
not in str(tag)):
count_url += 1
add_url = "https://www.wattpad.com" + tag["href"] + " "
match = re.search(r'\d+', add_url)
url_id = match.group()
id_list.append(url_id)
storys_url += add_url
print("[" + str(count_url) + "] " + tag.text +
" added to list. Url: https://www.wattpad.com" + tag["href"])
p_green("[I] Redirect to download script")
os.system("python scrape.py " + type_save + " " + storys_url)
p_green("[I] Directory Organization...")
try:
os.mkdir(os.getcwd() + "/downloads")
except:
aa = 0
try:
os.mkdir(os.getcwd() + "/lists")
except:
aa = 0
try:
os.mkdir(os.getcwd() + "/lists/" + url_id + " - " +
save_file.rename_valid_f(list_name))
except:
aa = 0
list_dir = os.listdir(path=os.getcwd() + "/downloads")
for file_d in list_dir:
if file_d.split(" ")[0] in id_list:
try:
shutil.copytree(
os.getcwd() + "/downloads/" + file_d,
os.getcwd() + "/lists/" + url_id + " - " +
save_file.rename_valid_f(list_name) + "/" + file_d)
except:
aa = 00
try:
shutil.copy(
os.getcwd() + "/downloads/" + file_d,
os.getcwd() + "/lists/" + url_id + " - " +
save_file.rename_valid_f(list_name) + "/")
except:
aa = 00
shutil.rmtree(os.getcwd() + "/downloads")
try:
os.rename("downloads_temp", "downloads")
except:
aa = 00
p_green("[I] List Folder Ready")
p_green("[I] " + list_name + " downloaded")