def mangareader(url, download_chapters, args):
html = get_html(url)
global last
if hasattr(args, 'last'):
last = args.last
series = title(
re.search('<td.*?>\\s*Name:.*?<h2.*?>\\s*(.*?)\\s*</h2>\\s*</td>',
html.replace('\n', '')).group(1))
status = re.search('<td.*?>\\s*Status:.*?<td>\\s*(.*?)\\s*</td>',
html.replace('\n', '')).group(1)
author = re.search('<td.*?>\\s*Author:.*?<td>\\s*(.*?)\\s*</td>',
html.replace('\n',
'')).group(1).partition('(')[0].strip()
tags = re.findall('<a.*?><span class="genretags">(.*?)</span></a>', html)
for j in range(len(tags)):
for k in tag_dict:
tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
for j in re.findall('<tr>\\s*<td>\\s*<div.*?</div>(.*?)</tr>', html,
re.DOTALL | re.MULTILINE):
match = re.search('<a.*?([\\d.,-]+)</a>(\\s*:\\s*)(.*?)\\s*</td>', j)
num = float(match.group(1))
name = match.group(3)
link = 'http://www.mangareader.net' + re.search(
'<a\\s*href=\"(/.*?)\">', j).group(1)
date = re.search('<td>(\\d{2})/(\\d{2})/(\\d{4})</td>', j)
date = '{:04}-{:02}-{:02}'.format(int(date.group(3)),
int(date.group(1)),
int(date.group(2)))
if name:
name = '{} - {} : {}'.format(series,
'{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters
and num in download_chapters) or (not download_chapters
and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(name))
chap_html = get_html(link)
links = [
'http://www.mangareader.net' + i for i in re.findall(
'<option value=\"(.*?)\".*?>\\d+</option>', chap_html)
]
chapters.append({
'name': name,
'links': links,
'backup_links': links,
'date': date,
'pages': len(links),
'num': num
})
if chapters:
function_name(chapters, series, tags, author, status, args)
def set_desc(self, chat_id, i, desc):
try:
self.plans[str(chat_id)][i]["desc"] = util.title(desc)
iomgr.save(PLANS_JSON, self.plans)
return "*Description is updated!* 😎"
except IndexError:
return False
except KeyError:
return False
def scan_fr(url, download_chapters,args):
print("getting url "+url)
html = get_html(url)
global last
if hasattr(args, 'last'):
last=args.last
series = title(re.search('(<h2 class="widget-title" style="display: inline-block;">)([^<]*)(</h2>)', html.replace('\n', '')).group(2))
print("series: series"+series)
#FIND ALL
# info_gen = re.findall('(<div class="cell">\\s*(.*?)\\s*</div>)', html.replace('\n', '')) ## ['*****@*****.**', '*****@*****.**']
status="" # not set in this source
author="" # not set in this source
tags="" # not set in this source
# for j in range(len(tags)):
#for k in tag_dict:
#tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
# catch chapters list
chapitres=re.search('(<ul class="chapters">(.*)</ul>)', html.replace('\n','').replace('\r',''))
# char ? will be used to allow overlapping regex !
for j in re.findall('<h5 class="chapter-title-rtl">(.*?)</h5>', chapitres.group(1), re.DOTALL|re.MULTILINE)[::-1]:
print("ligne trouvée:"+j)
#match = re.search('<a.*[-/]([0-9]+).*',j,re.DOTALL|re.MULTILINE)
match = re.search('<a.*[-/]([0-9.]+).*>(.*) ([0-9.]+)</a>',j,re.DOTALL|re.MULTILINE)
# re.search('<a.*?>(.*?)([\\d,.]+)\\s*</a>', j, re.DOTALL|re.MULTILINE)
#name = match.group(2)
num = float(match.group(1))
link = "http://"+re.search('href=\".*(www.*?)\"', j).group(1)
# no name, we use title instead
name = ''
date = "01/01/2000"
serie_short=match.group(2)
if name:
name = '{} - {} : {}'.format(serie_short, '{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters and num in download_chapters) or (not download_chapters and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(series))
print(' downloading chapter '+link)
chap_html = get_html(link)
links=['']
image_regex="data-src='(.*?) '"
links = [i for i in re.findall(image_regex, chap_html)]
chapters.append({'name':name, 'links':links, 'backup_links':links, 'date':date, 'pages':len(links), 'num':num})
args.url=url
if chapters:
function_name(chapters, series, tags, author, status,args)
def goodmanga(url, download_chapters,args):
html = get_html(url)
global last
if hasattr(args, 'last'):
last=args.last
series = title(re.search('<h1>([^<>]*?)</h1>', html.replace('\n', '')).group(1))
status = re.search('<span>Status:</span>\\s*(.*?)\\s*</div>', html.replace('\n', '')).group(1)
author = re.search('<span>Authors?:</span>\\s*(.*?)\\s*</div>', html.replace('\n', '')).group(1)
tags = re.findall('<a.*?>(.*?)</a>', re.search('<span>Genres:</span>(.*?)\\s*</div>', html, re.DOTALL|re.MULTILINE).group(1))
for j in range(len(tags)):
for k in tag_dict:
tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
while True:
for j in re.findall('<li>\\s*(.{1,300}?\\d{4}</span>)\\s*</li>', html, re.DOTALL|re.MULTILINE):
match = re.search('<a.*?>.*?([\\d,.]+)\\s*</a>\\s*<span.*?>\\s*(.*?)\\s*</span>', j, re.DOTALL|re.MULTILINE)
name = match.group(2)
num = float(match.group(1))
link = re.search('href=\"(.*?)\"', j).group(1)
try:
date = datetime.strptime(re.search('([A-Za-z]*? \\d{1,2}, \\d{4})</span>', j).group(1), '%b %d, %Y').strftime('%Y-%m-%d')
except:
date = datetime.datetime.today().strftime('%Y-%m-%d')
if name:
name = '{} - {} : {}'.format(series, '{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters and num in download_chapters) or (not download_chapters and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(name))
chap_html = get_html(link)
img_url = re.sub('1.([jpgnig]{3})', '{}.\\1', re.search('</div>\\s*<a.*?>\\s*<img[^<]*?src=\"(.*?)\".*?>\\s*</a>', chap_html, re.DOTALL|re.MULTILINE).group(1))
pages = max([int(i) for i in re.findall('<option value=\".*?\".*?>\\s*(\\d+)\\s*</option>', chap_html)])
b_links = {float(i[1]):i[0] for i in re.findall('<option value=\"(.*?)\".*?>\\s*(\\d+)\\s*</option>', chap_html)}
b_links = [b_links[i+1] for i in range(pages)]
links = [img_url.format(i+1) for i in range(pages)]
chapters.insert(0, {'name':name, 'links':links, 'backup_links':b_links, 'date':date, 'pages':pages, 'num':num})
match = re.search('<a href=\"(.*?)\">Next</a>', html)
if match:
html = get_html(match.group(1))
else:
break
if chapters:
function_name(chapters, series, tags, author, status,args)
def new_plan(self, chat_id, desc, place, time):
chat_id = str(chat_id)
if chat_id not in self.plans:
self.plans[chat_id] = []
# util.insert_new_plan(self.plans[chat_id], {"desc": util.title(desc),
# "loc": place,
# "dt": time})
self.plans[chat_id].append({
"desc": util.title(desc),
"loc": place,
"dt": time
})
self.plans[chat_id] = sort_plans(self.plans[chat_id])
print("Added a new event!")
iomgr.save(PLANS_JSON, self.plans)
def japscan(url, download_chapters, args):
print("getting url " + url)
html = get_html(url)
global last
if hasattr(args, 'last'):
last = args.last
series = title(
re.search('(<h1 class="bg-header">).*>(.*)</a>(</h1>)',
html.replace('\n', '')).group(2))
#FIND ALL
info_gen = re.findall('(<div class="cell">\\s*(.*?)\\s*</div>)',
html.replace(
'\n',
'')) ## ['*****@*****.**', '*****@*****.**']
status = info_gen[7][1]
author = info_gen[5][1]
tags = info_gen[7][1]
# for j in range(len(tags)):
#for k in tag_dict:
#tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
# catch chapters list
chapitres = re.search(
'(<div id="liste_chapitres">(.*)</div>.*<div class="col-1-3")',
html.replace('\n', ''))
#print(html)
#print(chapitres.group(1))
for j in re.findall('<li>(.*?)</li>', chapitres.group(1),
re.DOTALL | re.MULTILINE)[::-1]:
#match = re.search('<a.*[-/]([0-9]+).*',j,re.DOTALL|re.MULTILINE)
match = re.search(
'<a.*[-/]([0-9.]+).*>Scan (.*) ([0-9.]+) VF( : )?(.*)?<.*', j,
re.DOTALL | re.MULTILINE)
# re.search('<a.*?>(.*?)([\\d,.]+)\\s*</a>', j, re.DOTALL|re.MULTILINE)
#name = match.group(2)
num = float(match.group(1))
link = "http://" + re.search('href=\".*(www.*?)\"', j).group(1)
name = match.group(5)
date = "01/01/2000"
serie_short = match.group(2)
if name:
name = '{} - {} : {}'.format(serie_short,
'{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters
and num in download_chapters) or (not download_chapters
and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(series))
chap_html = get_html(link)
links = ['']
#HACK : HAVE TO PARSE EACH PAGE TO RETRIEVE IMAGE
for content in re.findall(
'<option .* value=\"(.*?)\".*?>.*</option>',
chap_html)[::-1]:
# print("http://www.japscan.com"+content)
content_html = get_html("http://www.japscan.com" + content)
search = '<div itemscope itemtype="http://schema.org/Article">.*src="(.*[.][a-z]{0,4})" />'
#link_page=re.search(search,content_html.replace('\n',''),re.MULTILINE)
link_page = re.search(search, content_html.replace('\n', ''),
re.MULTILINE)
#print(content_html.replace('\n',''))
try:
#print(link_page.group(1))
links.append(link_page.group(1))
except:
print('An error occurs, unable to search pages')
print(content_html.replace('\n', ''))
links.remove('')
links = list(reversed(links))
chapters.append({
'name': name,
'links': links,
'backup_links': links,
'date': date,
'pages': len(links),
'num': num
})
args.url = url
if chapters:
function_name(chapters, series, tags, author, status, args)
def mymanga(url, download_chapters, args):
html = get_html(url)
global last
if hasattr(args, 'last'):
last = args.last
series = title(
re.search('(<h2 class="text-border">)(.*)(</h2>)',
html.replace('\n', '')).group(2))
#FIND ALL
info_gen = re.findall('(<div class="cell">\\s*(.*?)\\s*</div>)',
html.replace(
'\n',
'')) ## ['*****@*****.**', '*****@*****.**']
status = 'default' #info_gen[7][1]
author = 'default' #info_gen[5][1]
tags = 'default' #info_gen[7][1]
# for j in range(len(tags)):
#for k in tag_dict:
#tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
# catch chapters list
chapitres = re.search(
'(<section class="listchapseries fiche block sep">(.*)</section>)',
html.replace('\n', ''))
#print(html.replace('\n',''))
#print(chapitres.group(1))
for j in re.findall('<li>(.*?)</li>', chapitres.group(1),
re.DOTALL | re.MULTILINE)[::-1]:
#match = re.search('<a.*[-/]([0-9]+).*',j,re.DOTALL|re.MULTILINE)
match = re.search('<a.* href=".*/chapitre-([0-9.]+)/', j,
re.DOTALL | re.MULTILINE)
# re.search('<a.*?>(.*?)([\\d,.]+)\\s*</a>', j, re.DOTALL|re.MULTILINE)
#name = match.group(2)
num = float(match.group(1))
link = "http://" + re.search('href=\".*(www.*?)\" title', j).group(1)
name = match.group(1)
date = "01/01/2000"
serie_short = series
if name:
name = '{} - {} : {}'.format(serie_short,
'{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters
and num in download_chapters) or (not download_chapters
and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(series))
chap_html = get_html(link)
links = ['']
#HACK : HAVE TO PARSE EACH PAGE TO RETRIEVE IMAGE
#print(chap_html)
for content in re.findall('<option value="(.*[0-9]?)" ',
chap_html)[::-1]:
#print("http://www.hitmanga.eu/"+content)
content_html = get_html("http://www.hitmanga.eu/" + content)
#print(content_html.replace('\n','').replace('\r',''))
search = '<table id="picture">.*src="(.*[.][a-z]{0,4}?)" alt=.*</table>'
#link_page=re.search(search,content_html.replace('\n',''),re.MULTILINE)
link_page = re.search(search, content_html.replace('\n', ''),
re.MULTILINE)
#print(content_html.replace('\n',''))
try:
#print(link_page.group(1))
links.append(link_page.group(1))
except:
print('An error occurs, unable to search pages')
print(content_html.replace('\n', ''))
links.remove('')
links = list(reversed(links))
chapters.append({
'name': name,
'links': links,
'backup_links': links,
'date': date,
'pages': len(links),
'num': num
})
args.url = url
if chapters:
function_name(chapters, series, tags, author, status, args)
def batoto(url, download_chapters,args):
batoto_username = args.username
batoto_password = args.password
login()
for i in range(3):
try:
html = get_html(url+'/')
break
except:
if i == 2:
raise
else:
pass
global last
global session
if hasattr(args, 'last'):
last=args.last
series = title(re.search('<h1.*?>[\\s\n]*(.*?)[\\s\n]*</h1>', html, re.DOTALL|re.MULTILINE).group(1))
status = re.search('<td.*?>Status:</td>\\s*<td>\\s*(.*?)\\s*</td>', html.replace('\n', '')).group(1)
author = ', '.join(re.findall('<a.*?>(.*?)</a>', re.search('<td.*?>\\s*Authors?\\s*:?\\s*</td>\\s*<td>(.*?)</td>', html.replace('\n', '')).group(1)))
tags = re.findall('<a.*?>\\s*<span.*?>\\s*([A-Za-z]*?)\\s*</span>\\s*</a>', re.search('<td.*?>\\s*Genres?\\s*:?\\s*</td>\\s*<td>(.*?)</td>', html.replace('\n', '')).group(1))
for j in range(len(tags)):
for k in tag_dict:
tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
for j in re.findall('<tr class=\"row lang_([A-Za-z]*?) chapter_row\".*?>(.*?)</tr>', html, re.DOTALL|re.MULTILINE)[::-1]:
if j[0] == batoto_lang:
match = re.search('<a href=\"([^\"]*?)\".*?>\\s*<img.*?>\\s*([^\"<>]*)(\\s*:\\s*)?(.*?)\\s*</a>', j[1], re.DOTALL|re.MULTILINE)
name = match.group(4)
m2 = re.search('[Cc]h(ap)?(ter)?\\.?\\s*([Ee]xtra:?)?\\s*([\\d\\.]+)\\s*(-\\s*[\\d\\.]+)?', match.group(2))
try:
num = float(m2.group(4))
except:
if args.debug:
print(j[1])
raise
'''
#TODO
if m2.group(3):
if chapters:
num = chapters[-1]['num'] + .4
else:
num = last + .4
'''
try:
vol = int(re.search('[Vv]ol(ume)?\\.\\s*(\\d+)', match.group(2)).group(2))
except:
vol = 0
link = match.group(1)
uuid = link.rpartition('#')[2]
ref = link.rpartition('/')[0]+'/' + "reader#" + uuid + "_1"
head = {'Referer':ref, 'supress_webtoon':'t'}
link = link.rpartition('/')[0]+'/'+ 'areader?id='+uuid+'&p=1'
session.headers.update(head)
try:
date = datetime.strptime(re.search('<td.*?>(\\d{2} [A-Za-z]* \\d{4}.*?([Aa][Mm]|[Pp][Mm])).*?</td>', j[1]).group(1), '%d %B %Y - %I:%M %p').strftime('%Y-%m-%dT%H:%M:00')
except:
try:
t = re.search('(\\d+) [Mm]inutes ago', j[1]).group(1)
except:
t = '1' if re.search('A minute ago', j[1]) else ''
if t:
unit = '%M'
else:
try:
t = re.search('(\\d+) [Hh]ours ago', j[1]).group(1)
except:
t = '1' if re.search('An hour ago', j[1]) else ''
if t:
unit = '%H'
else:
try:
t = re.search('(\\d+) [Dd]ays ago', j[1]).group(1)
except:
t = '1' if re.search('A day ago', j[1]) else ''
if t:
unit = '%d'
else:
try:
t = re.search('(\\d+) [Ww]eeks ago', j[1]).group(1)
except:
t = '1' if re.search('A week ago', j[1]) else ''
if t:
unit = '%W'
else:
t = '0'
unit = '%M'
date = datetime.fromtimestamp((datetime.today()-datetime.strptime(t, unit)).total_seconds()).strftime('%Y-%m-%dT%H:%M:00')
if name:
name = '{} - {} : {}'.format(series, '{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters and num in download_chapters) or (not download_chapters and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(name))
chap_html = get_html(link)
img_url = re.sub('001\\.([A-Za-z]{3})', '{:03}.\\1', re.search('<div.*?>\\s*<a.*?>\\s*<img[^<]*?src=\"([^\"]*?)\"[^>]*?/>\\s*</div>', chap_html, re.DOTALL|re.MULTILINE).group(1))
zero = False
if '{:03}' not in img_url:
img_url = re.sub('000\\.([A-Za-z]{3})', '{:03}.\\1', img_url)
zero = True
if '{:03}' not in img_url:
img_url = re.sub('000\\.([A-Za-z]{3})', '{:03}.\\1', img_url)
zero = True
if '{:03}' not in img_url:
img_url = re.sub('01\\.([A-Za-z]{3})', '{:02}.\\1', img_url)
zero = False
if '{:02}' not in img_url:
img_url = re.sub('00\\.([A-Za-z]{3})', '{:02}.\\1', img_url)
zero = True
if re.findall('<option value=\".*?\".*?>page (\\d+)</option>', chap_html):
pages = max([int(i) for i in re.findall('<option value=\".*?\".*?>page (\\d+)</option>', chap_html)])
else:
continue
b_links = {float(i[1]):i[0] for i in re.findall('<option value=\"(.*?)\".*?>page (\\d+)</option>', chap_html)}
b_links = [b_links[i+1] for i in range(pages)]
if zero:
links = [img_url.format(i) for i in range(pages)]
else:
links = [img_url.format(i+1) for i in range(pages)]
chapters.append({'name':name, 'links':links, 'backup_links':b_links, 'date':date, 'pages':pages, 'num':num})
if chapters:
function_name(chapters, series, tags, author, status,args)
def mangahere(url, download_chapters, args):
html = get_html(url)
global last
if hasattr(args, 'last'):
last = args.last
series = title(
re.search(
'<h1 class="title"><span class="title_icon"></span>(.*?)</h1>',
html.replace('\n', '')).group(1))
status = re.search('<li><label>Status:</label>(.*?)<',
html.replace('\n', '')).group(1)
author = ', '.join(
re.findall(
'<a.*?>(.*?)</a>',
re.search('<li><label>Author\\(?s?\\)?:</label>(.*?)</li>',
html.replace('\n', '')).group(1)))
tags = re.search('<li><label>Genre\\(s\\):</label>(.*?)</li>',
html).group(1).split(', ')
for j in range(len(tags)):
for k in tag_dict:
tags[j] = re.sub(k, tag_dict[k], tags[j])
chapters = []
for j in re.findall(
'<li>\\s*<span class=\"left\">\\s*(.*?\\d{4}</span>)\\s*</li>',
html, re.DOTALL | re.MULTILINE)[::-1]:
match = re.search(
'<a.*?>.*?([\\d,.]+)\\s*</a>\\s*<span.*?>\\s*(.*?)\\s*</span>', j,
re.DOTALL | re.MULTILINE)
name = match.group(2)
num = float(match.group(1))
link = re.search('href=\"(.*?)\"', j).group(1)
try:
date = datetime.strptime(
re.search('([A-Za-z]*? \\d{1,2}, \\d{4})</span>', j).group(1),
'%b %d, %Y').strftime('%Y-%m-%d')
except:
date = datetime.datetime.today().strftime('%Y-%m-%d')
if name:
name = '{} - {} : {}'.format(series,
'{:3.1f}'.format(num).zfill(5), name)
else:
name = '{} - {}'.format(series, '{:3.1f}'.format(num).zfill(5))
if (download_chapters
and num in download_chapters) or (not download_chapters
and num > last):
if args.debug or args.verbose:
print(' Gathering info: \"{}\"'.format(name))
chap_html = get_html(link)
img_url = re.sub(
'001.([A-Za-z]{3})', '{:03}.\\1',
re.search('<a.*?>\\s*<img[^<]*?src=\"(.*?)\".*?>\\s*</a>',
chap_html, re.DOTALL | re.MULTILINE).group(1))
if '{:03}' not in img_url:
img_url = re.sub('01.([A-Za-z]{3})', '{:02}.\\1', img_url)
pages = max([
int(i) for i in re.findall(
'<option value=\".*?\".*?>(\\d+)</option>', chap_html)
])
b_links = {
float(i[1]): i[0]
for i in re.findall(
'<option value=\"(.*?)\".*?>(\\d+)</option>', chap_html)
}
b_links = [b_links[i + 1] for i in range(pages)]
links = [img_url.format(i + 1) for i in range(pages)]
chapters.append({
'name': name,
'links': links,
'backup_links': b_links,
'date': date,
'pages': pages,
'num': num
})
if chapters:
function_name(chapters, series, tags, author, status, args)