def getLyrics(track, artist):
"""
Returns a dictionary with possible keys:
lyrics
If no match found, returns empty dictionary
"""
track = track.encode('utf-8')
artist = artist.encode('utf-8')
url = 'http://www.pandora.com/music/song/%s/%s' % (urllib.quote_plus(
artist.lower()), urllib.quote_plus(track.lower()))
ret = getSourceCode(url)
try:
trackUid = regex_trackUid.search(ret).group(1)
intermMatch = regex_lyricIdCheckSum.search(ret)
lyricId = intermMatch.group(1)
checkSum = intermMatch.group(2)
nonExplicit = 'false'
authToken = 'null'
except AttributeError:
return {}
else:
return __getEncryptedLyrics(trackUid, lyricId, checkSum, nonExplicit,
authToken)
def downloadChapter(self, downloadThread, max_pages, url, manga_chapter_prefix, current_chapter): pageIndex = 0 for page in MangaPanda.re_getPage.findall(getSourceCode(url, self.proxy)): if (self.verbose_FLAG): print(self.chapters[current_chapter][1] + ' | ' + 'Page %s / %i' % (page[1], max_pages)) pageUrl = 'http://www.mangapanda.com' + page[0] self.downloadImage(downloadThread, page[1], pageUrl, manga_chapter_prefix) pageIndex = pageIndex + 1
def downloadChapter(self, downloadThread, max_pages, url, manga_chapter_prefix, current_chapter): pageIndex = 0 for page in MangaReader.re_getPage.findall(getSourceCode(url, self.proxy)): if (self.verbose_FLAG): print(self.chapters[current_chapter][1] + ' | ' + 'Page %s / %i' % (page[1], max_pages)) pageUrl = 'http://www.mangareader.net' + page[0] self.downloadImage(downloadThread, page[1], pageUrl, manga_chapter_prefix) pageIndex = pageIndex + 1
def parseSite(self):
print('Beginning MangaPanda check: %s' % self.manga)
url = 'http://www.mangapanda.com/alphabetical'
source = getSourceCode(url, self.proxy)
allSeries = MangaPanda.re_getSeries.findall(
source[source.find('series_col'):])
keyword = self.selectFromResults(allSeries)
url = 'http://www.mangapanda.com%s' % keyword
source = getSourceCode(url, self.proxy)
self.chapters = MangaPanda.re_getChapters.findall(source)
lowerRange = 0
for i in range(0, len(self.chapters)):
self.chapters[i] = ('http://www.mangapanda.com%s' %
self.chapters[i][0], '%s%s' %
(self.chapters[i][1], self.chapters[i][2]),
self.chapters[i][1])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
self.isPrependMangaName = False
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
self.isPrependMangaName = True
return
def downloadAnimea(self, manga, chapter_start, chapter_end, download_path, download_format):
for current_chapter in range(chapter_start, chapter_end + 1):
manga_chapter_prefix = manga.lower().replace('-', '_') + '_' + str(current_chapter).zfill(3)
if (os.path.exists(download_path + manga_chapter_prefix + '.cbz') or os.path.exists(download_path + manga_chapter_prefix + '.zip')) and overwrite_FLAG == False:
print('Chapter ' + str(current_chapter) + ' already downloaded, skipping to next chapter...')
continue;
url = 'http://manga.animea.net/'+ manga + '-chapter-' + str(current_chapter) + '-page-1.html'
source = getSourceCode(url)
max_pages = int(re.compile('of (.*?)</title>').search(source).group(1))
for page in range(1, max_pages + 1):
url = 'http://manga.animea.net/'+ manga + '-chapter-' + str(current_chapter) + '-page-' + str(page) + '.html'
source = getSourceCode(url)
img_url = re.compile('img src="(http.*?.[jp][pn]g)"').search(source).group(1)
print('Chapter ' + str(current_chapter) + ' / ' + 'Page ' + str(page))
print(img_url)
downloadImage(img_url, os.path.join('mangadl_tmp', manga_chapter_prefix + '_' + str(page).zfill(3)))
compress(manga_chapter_prefix, download_path, max_pages, download_format)
def downloadChapter(self, downloadThread, max_pages, url, manga_chapter_prefix, current_chapter):
"""We ignore max_pages, because you can't regex-search that under Batoto."""
s = getSourceCode(url, self.proxy)
soup = BeautifulSoup(s)
ol = soup.find("select", id="page_select")("option")
n = 1
for i in ol:
if self.verbose_FLAG:
print(i['value'])
self.downloadImage(downloadThread, n, i['value'], manga_chapter_prefix)
n += 1
def downloadChapter(self, downloadThread, max_pages, url, manga_chapter_prefix, current_chapter):
"""We ignore max_pages, because you can't regex-search that under Batoto."""
s = getSourceCode(url, self.proxy)
soup = BeautifulSoup(s)
ol = soup.find("select", id="page_select")("option")
n = 1
for i in ol:
if self.verbose_FLAG:
print(i['value'])
self.downloadImage(downloadThread, n, i['value'], manga_chapter_prefix)
n += 1
def parseSite(self):
print('Beginning OtakuWorks check: %s' % self.manga)
url = 'http://www.otakuworks.com/search/%s' % '+'.join(self.manga.split())
source = getSourceCode(url)
info = OtakuWorks.re_getMangas.findall(source)
# we either have 0 search results or we have already been redirected to the manga homepage
if len(info) != 0:
keyword = self.selectFromResults(info)
source = getSourceCode(keyword)
if(source.find('has been licensed and as per request all releases under it have been removed.') != -1):
raise self.MangaNotFound('It has been removed.')
# can't pre-compile this because relies on class name
self.chapters = re.compile('a href="([^>]*%s[^>]*)">([^<]*#([^<]*))</a>' % '-'.join(fixFormatting(self.manga, '.').replace('_', ' ').split())).findall(source)
self.chapters.reverse()
lowerRange = 0
for i in range(0, len(self.chapters)):
self.chapters[i] = ('http://www.otakuworks.com' + self.chapters[i][0] + '/read', self.chapters[i][1], self.chapters[i][2])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
else:
if ( lowerRange == upperRange):
raise self.NoUpdates
for i in range (lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
print('Beginning MangaPanda check: %s' % self.manga)
url = 'http://www.mangapanda.com/alphabetical'
source = getSourceCode(url, self.proxy)
allSeries = MangaPanda.re_getSeries.findall(source[source.find('series_col'):])
keyword = self.selectFromResults(allSeries)
url = 'http://www.mangapanda.com%s' % keyword
source = getSourceCode(url, self.proxy)
self.chapters = MangaPanda.re_getChapters.findall(source)
lowerRange = 0
for i in range(0, len(self.chapters)):
self.chapters[i] = ('http://www.mangapanda.com%s' % self.chapters[i][0], '%s%s' % (self.chapters[i][1], self.chapters[i][2]), self.chapters[i][1])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
self.isPrependMangaName = False
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range (lowerRange, upperRange):
self.chapters_to_download .append(i)
self.isPrependMangaName = True
return
def downloadChapter(self, downloadThread, max_pages, url,
manga_chapter_prefix, current_chapter):
pageIndex = 0
pages = EatManga.re_getPage.findall(getSourceCode(url, self.proxy))
#Remove duplicate pages if any and ensure order
pages = list(OrderedDict.fromkeys(pages))
for page in pages:
if (self.verbose_FLAG):
print(self.chapters[current_chapter][1] + ' | ' +
'Page %s / %i' % (page[1], max_pages))
pageUrl = 'http://eatmanga.com%s' % page[0]
self.downloadImage(downloadThread, page[1], pageUrl,
manga_chapter_prefix)
pageIndex = pageIndex + 1
def parseSite(self):
print('Beginning EatManga check: %s' % self.manga)
url = 'http://eatmanga.com/Manga-Scan/%s' % self.fixFormatting(
self.manga)
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
self.chapters = EatManga.re_getChapters.findall(source)
self.chapters.reverse()
if not self.chapters:
raise self.MangaNotFound
lowerRange = 0
for i in range(0, len(self.chapters)):
if 'upcoming' in self.chapters[i][0]:
#Skip not available chapters
del self.chapters[i]
continue
self.chapters[i] = ('http://eatmanga.com%s' % self.chapters[i][0],
self.chapters[i][2], self.chapters[i][2])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
self.isPrependMangaName = True
return
def __getEncryptedLyrics(trackUid, lyricId, checkSum, nonExplicit, authToken):
url = "http://www.pandora.com/services/ajax/?"
url += urllib.urlencode({ 'method' :'lyrics.getLyrics',
'trackUid' :trackUid,
'checkSum' :checkSum,
'nonExplicit' :nonExplicit,
'authToken' :authToken })
ret = getSourceCode(url)
decryptionKey = re.search('var k="([^"]*)"', ret).group(1)
# functions in javascript can contain ", which makes python dictionary
# parsing throw errors, workaround by replacing them out
ret = re.sub('(function[^,]*)', '0', ret).replace('\\u00',r'\x')
# use ast.literal_eval vs. eval because it's safer
encrypted = ast.literal_eval(ret)
encryptedLyrics= encrypted['lyrics']
return __decryptLyrics(encryptedLyrics, decryptionKey)
def __getEncryptedLyrics(trackUid, lyricId, checkSum, nonExplicit, authToken):
url = "http://www.pandora.com/services/ajax/?"
url += urllib.urlencode({
'method': 'lyrics.getLyrics',
'trackUid': trackUid,
'checkSum': checkSum,
'nonExplicit': nonExplicit,
'authToken': authToken
})
ret = getSourceCode(url)
decryptionKey = re.search('var k="([^"]*)"', ret).group(1)
# functions in javascript can contain ", which makes python dictionary
# parsing throw errors, workaround by replacing them out
ret = re.sub('(function[^,]*)', '0', ret).replace('\\u00', r'\x')
# use ast.literal_eval vs. eval because it's safer
encrypted = ast.literal_eval(ret)
encryptedLyrics = encrypted['lyrics']
return __decryptLyrics(encryptedLyrics, decryptionKey)
def getLyrics(track, artist):
"""
Returns a dictionary with possible keys:
lyrics
If no match found, returns empty dictionary
"""
track = track.encode('utf-8')
artist = artist.encode('utf-8')
url = 'http://www.pandora.com/music/song/%s/%s' % (urllib.quote_plus(artist.lower()),
urllib.quote_plus(track.lower()))
ret = getSourceCode(url)
try:
trackUid = regex_trackUid.search(ret).group(1)
intermMatch = regex_lyricIdCheckSum.search(ret)
lyricId = intermMatch.group(1)
checkSum = intermMatch.group(2)
nonExplicit = 'false'
authToken = 'null'
except AttributeError:
return {}
else:
return __getEncryptedLyrics(trackUid, lyricId, checkSum, nonExplicit, authToken)
def get_next_url(self, c):
s = getSourceCode(c, self.proxy)
soup = BeautifulSoup(s)
l = soup.find("img", title="Next Chapter").parent
return l['href']
def parseSite(self):
"""
Parses list of chapters and URLs associated with each one for the given manga and site.
"""
print('Beginning MangaHere check: %s' % self.manga)
# jump straight to expected URL and test if manga removed
url = 'http://www.mangahere.com/manga/%s/' % self.fixFormatting(
self.manga)
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if (source is None or 'the page you have requested can' in source):
# do a 'begins-with' search, then a 'contains' search
url = 'http://www.mangahere.com/search.php?name=%s' % '+'.join(
self.manga.split())
if self.verbose_FLAG:
print(url)
try:
source = getSourceCode(url, self.proxy)
seriesResults = MangaHere.re_getSeries.findall(source)
seriesResults = []
if source is not None:
seriesResults = MangaHere.re_getSeries.findall(source)
if (0 == len(seriesResults)):
url = 'http://www.mangahere.com/search.php?name=%s' % '+'.join(
self.manga.split())
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if source is not None:
seriesResults = MangaHere.re_getSeries.findall(source)
# 0 results
except AttributeError:
raise self.MangaNotFound(
'It doesn\'t exist, or cannot be resolved by autocorrect.')
else:
keyword = self.selectFromResults(seriesResults)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
url = 'http://www.mangahere.com/manga/%s/' % keyword
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
else:
# The Guess worked
keyword = self.fixFormatting(self.manga)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
# other check for manga removal if our initial guess for the name was wrong
if ('it is not available in.' in source):
raise self.MangaNotFound('It has been removed.')
# that's nice of them
#url = 'http://www.mangahere.com/cache/manga/%s/chapters.js' % keyword
#source = getSourceCode(url, self.proxy)
# chapters is a 2-tuple
# chapters[0] contains the chapter URL
# chapters[1] contains the chapter title
isChapterOnly = False
# can't pre-compile this because relies on class name
re_getChapters = re.compile(
'a.*?href="http://.*?mangahere.*?/manga/%s/(v[\d]+)/(c[\d]+)/[^"]*?"'
% keyword)
self.chapters = re_getChapters.findall(source)
if not self.chapters:
if self.verbose_FLAG:
print("Trying chapter only regex")
isChapterOnly = True
re_getChapters = re.compile(
'a.*?href="http://.*?mangahere.*?/manga/%s/(c[\d]+)/[^"]*?"' %
keyword)
self.chapters = re_getChapters.findall(source)
self.chapters.reverse()
# code used to both fix URL from relative to absolute as well as verify last downloaded chapter for XML component
lowerRange = 0
if isChapterOnly:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s" % self.chapters[i])
if (self.auto):
if (self.lastDownloaded == self.chapters[i]):
lowerRange = i + 1
self.chapters[i] = ('http://www.mangahere.com/manga/%s/%s' %
(keyword, self.chapters[i]),
self.chapters[i], self.chapters[i])
else:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s %s" % (self.chapters[i][0], self.chapters[i][1]))
self.chapters[i] = (
'http://www.mangahere.com/manga/%s/%s/%s' %
(keyword, self.chapters[i][0], self.chapters[i][1]),
self.chapters[i][0] + "." + self.chapters[i][1],
self.chapters[i][1])
if (self.auto):
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
# Validate whether the last chapter is a
if (self.verbose_FLAG):
print(self.chapters[upperRange - 1])
print("Validating chapter: %s" % self.chapters[upperRange - 1][0])
source = getSourceCode(self.chapters[upperRange - 1][0], self.proxy)
if ('not available yet' in source):
# If the last chapter is not available remove it from the list
del self.chapters[upperRange - 1]
upperRange = upperRange - 1
# which ones do we want?
if (not self.auto):
for i in range(0, upperRange):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
"""
Parses list of chapters and URLs associated with each one for the given manga and site.
"""
print('Beginning MangaFox check: %s' % self.manga)
# jump straight to expected URL and test if manga removed
url = 'http://mangafox.me/manga/%s/' % self.fixFormatting(self.manga)
if self.verbose_FLAG:
print(url)
source, redirectURL = getSourceCode(url, self.proxy, True)
if (redirectURL != url or source is None
or 'the page you have requested cannot be found' in source):
# Could not find the manga page by guessing
# Use the website search
url = 'http://mangafox.me/search.php?name_method=bw&name=%s&is_completed=&advopts=1' % '+'.join(
self.manga.split())
if self.verbose_FLAG:
print(url)
try:
source = getSourceCode(url, self.proxy)
seriesResults = []
if source is not None:
seriesResults = MangaFox.re_getSeries.findall(source)
if (0 == len(seriesResults)):
url = 'http://mangafox.me/search.php?name_method=cw&name=%s&is_completed=&advopts=1' % '+'.join(
self.manga.split())
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if source is not None:
seriesResults = MangaFox.re_getSeries.findall(source)
# 0 results
except AttributeError:
raise self.MangaNotFound(
'It doesn\'t exist, or cannot be resolved by autocorrect.')
else:
keyword = self.selectFromResults(seriesResults)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
url = 'http://mangafox.me/manga/%s/' % keyword
if self.verbose_FLAG:
print("URL: %s" % url)
source = getSourceCode(url, self.proxy)
if (source is None):
raise self.MangaNotFound('Search Failed to find Manga.')
else:
# The Guess worked
keyword = self.fixFormatting(self.manga)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
if ('it is not available in Manga Fox.' in source):
raise self.MangaNotFound('It has been removed.')
# that's nice of them
#url = 'http://mangafox.me/cache/manga/%s/chapters.js' % keyword
#source = getSourceCode(url, self.proxy)
# chapters is a 2-tuple
# chapters[0] contains the chapter URL
# chapters[1] contains the chapter title
isChapterOnly = False
# can't pre-compile this because relies on class name
re_getChapters = re.compile(
'a href="http://.*?mangafox.*?/manga/%s/(v[\d]+)/(c[\d]+)/[^"]*?" title'
% keyword)
self.chapters = re_getChapters.findall(source)
if not self.chapters:
if self.verbose_FLAG:
print("Trying chapter only regex")
isChapterOnly = True
re_getChapters = re.compile(
'a href="http://.*?mangafox.*?/manga/%s/(c[\d]+)/[^"]*?" title'
% keyword)
self.chapters = re_getChapters.findall(source)
self.chapters.reverse()
# code used to both fix URL from relative to absolute as well as verify last downloaded chapter for XML component
lowerRange = 0
if isChapterOnly:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s" % self.chapters[i])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i]))
else:
if (self.lastDownloaded == self.chapters[i]):
lowerRange = i + 1
self.chapters[i] = ('http://mangafox.me/manga/%s/%s' %
(keyword, self.chapters[i]),
self.chapters[i], self.chapters[i])
else:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s %s" % (self.chapters[i][0], self.chapters[i][1]))
self.chapters[i] = (
'http://mangafox.me/manga/%s/%s/%s' %
(keyword, self.chapters[i][0], self.chapters[i][1]),
self.chapters[i][0] + "." + self.chapters[i][1],
self.chapters[i][1])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
# which ones do we want?
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
print("Beginning Batoto check: {}".format(self.manga))
url = "http://www.batoto.net/search?name={}&name_cond=c".format('+'.join(self.manga.split()))
s = getSourceCode(url, self.proxy)
soup = BeautifulSoup(s)
a = soup.find("div", id="comic_search_results")
r = a.tbody.find_all("tr")[1:]
seriesl = []
try:
for i in r:
u = i.td.a['href']
t = i.td.a.img.next_sibling[1:]
seriesl.append((u,t.encode('utf-8')))
except TypeError:
# signifies no manga found
raise self.MangaNotFound("Nonexistent.")
manga = self.selectFromResults(seriesl)
if self.verbose_FLAG:
print(manga)
mname = [i for i in seriesl if i[0] == manga][0][1]
s = getSourceCode(manga, self.proxy)
soup = BeautifulSoup(s)
t = soup.find("table", class_="chapters_list").tbody
cl = t.find_all("tr", class_="lang_English")
self.chapters = [[]]
cnum = self.chapters[0]
for i in cl:
u = i.td.a['href']
t = i.td.a.img.next_sibling[1:]
g = i.find_all("td")[2].get_text().strip()
try:
c = float(re.search("ch([\d.]+)", u).group(1))
except AttributeError:
c = 0
tu = (u,t,g,c)
if len(cnum) == 0 or cnum[0][3] == c:
cnum.append(tu)
else:
self.chapters.append([])
cnum = self.chapters[-1]
cnum.append(tu)
self.chapters.reverse()
sc = None
for i in self.chapters:
if len(i) == 1 or sc == None:
if sc != None and sc[2] != i[0][2]:
if self.verbose_FLAG:
print("switched to {} at {}".format(i[0][2], i[0][3]))
sc = i[0]
del i[1:]
continue
ll = [n for n in i if n[2] == sc[2]]
if len(ll) != 1:
c = self.get_next_url(sc[0])
i[0] = [n for n in i if n[0] == c][0]
if self.verbose_FLAG:
print("Anomaly at chapter {} ({} matches, chose {})".format(i[0][3], len(ll), i[0][2]))
del i[1:]
sc = i[0]
continue
i[0] = ll[0]
sc = i[0]
del i[1:]
self.chapters = [i[0] for i in self.chapters]
for n,c in enumerate(self.chapters):
print("{:03d}. {}".format(n+1, c[1].encode('utf-8')))
self.chapters_to_download = self.selectChapters(self.chapters)
def parseSite(self):
print("Beginning Batoto check: {0}".format(self.manga))
url = "http://www.batoto.net/search?name={0}&name_cond=c".format(
'+'.join(self.manga.split()))
s = getSourceCode(url, self.proxy)
soup = BeautifulSoup(s)
a = soup.find("div", id="comic_search_results")
r = a.tbody.find_all("tr")[1:]
seriesl = []
for i in r:
try:
e = i.td.findAll('a')[1]
u = e['href']
t = e.img.next_sibling[1:]
seriesl.append((u, t.encode('utf-8')))
except:
pass
if not seriesl:
# signifies no manga found
raise self.MangaNotFound("Nonexistent.")
manga = self.selectFromResults(seriesl)
if self.verbose_FLAG:
print(manga)
mname = [i for i in seriesl if i[0] == manga][0][1]
s = getSourceCode(manga, self.proxy)
soup = BeautifulSoup(s)
t = soup.find("table", class_="chapters_list").tbody
cl = t.find_all("tr", class_="lang_English")
self.chapters = [[]]
cnum = self.chapters[0]
for i in cl:
u = i.td.a['href']
t = i.td.a.img.next_sibling[1:]
g = i.find_all("td")[2].get_text().strip()
try:
c = float(re.search("ch([\d.]+)", u).group(1))
c = str(int(c)) if c.is_integer() else str(c)
except AttributeError:
c = 0
tu = (u, t, c, g)
if len(cnum) == 0 or cnum[0][3] == c:
cnum.append(tu)
else:
self.chapters.append([])
cnum = self.chapters[-1]
cnum.append(tu)
self.chapters.reverse()
#Look for first chapter that should be downloaded in auto mode
lowerRange = 0
if (self.auto):
for i in range(0, len(self.chapters)):
if (self.lastDownloaded == self.chapters[i][0][1]):
lowerRange = i + 1
sc = None
for i in self.chapters:
if len(i) == 1 or sc == None:
if sc != None and sc[2] != i[0][2]:
if self.verbose_FLAG:
print("switched to {0} at {1}".format(
i[0][2], i[0][3]))
sc = i[0]
del i[1:]
continue
ll = [n for n in i if n[2] == sc[2]]
if len(ll) != 1:
c = self.get_next_url(sc[0])
i[0] = [n for n in i if n[0] == c][0]
if self.verbose_FLAG:
print("Anomaly at chapter {0} ({1} matches, chose {2})".
format(i[0][3], len(ll), i[0][2]))
del i[1:]
sc = i[0]
continue
i[0] = ll[0]
sc = i[0]
del i[1:]
self.chapters = [i[0] for i in self.chapters]
upperRange = len(self.chapters)
# which ones do we want?
if (not self.auto):
for n, c in enumerate(self.chapters):
print("{0:03d}. {1}".format(n + 1, c[1].encode('utf-8')))
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if (lowerRange == upperRange):
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
print("Beginning Batoto check: {}".format(self.manga))
url = "http://www.batoto.net/search?name={}&name_cond=c".format('+'.join(self.manga.split()))
s = getSourceCode(url, self.proxy)
soup = BeautifulSoup(s)
a = soup.find("div", id="comic_search_results")
r = a.tbody.find_all("tr")[1:]
seriesl = []
for i in r:
try:
e = i.td.findAll('a')[1]
u = e['href']
t = e.img.next_sibling[1:]
seriesl.append((u,t.encode('utf-8')))
except:
pass
if not seriesl:
# signifies no manga found
raise self.MangaNotFound("Nonexistent.")
manga = self.selectFromResults(seriesl)
if self.verbose_FLAG:
print(manga)
mname = [i for i in seriesl if i[0] == manga][0][1]
s = getSourceCode(manga, self.proxy)
soup = BeautifulSoup(s)
t = soup.find("table", class_="chapters_list").tbody
cl = t.find_all("tr", class_="lang_English")
self.chapters = [[]]
cnum = self.chapters[0]
for i in cl:
u = i.td.a['href']
t = i.td.a.img.next_sibling[1:]
g = i.find_all("td")[2].get_text().strip()
try:
c = float(re.search("ch([\d.]+)", u).group(1))
c = str(int(c)) if c.is_integer() else str(c)
except AttributeError:
c = 0
tu = (u,t,c,g)
if len(cnum) == 0 or cnum[0][3] == c:
cnum.append(tu)
else:
self.chapters.append([])
cnum = self.chapters[-1]
cnum.append(tu)
self.chapters.reverse()
#Look for first chapter that should be downloaded in auto mode
lowerRange = 0
if (self.auto):
for i in range(0, len(self.chapters)):
if (self.lastDownloaded == self.chapters[i][0][1]):
lowerRange = i + 1
sc = None
for i in self.chapters:
if len(i) == 1 or sc == None:
if sc != None and sc[2] != i[0][2]:
if self.verbose_FLAG:
print("switched to {} at {}".format(i[0][2], i[0][3]))
sc = i[0]
del i[1:]
continue
ll = [n for n in i if n[2] == sc[2]]
if len(ll) != 1:
c = self.get_next_url(sc[0])
i[0] = [n for n in i if n[0] == c][0]
if self.verbose_FLAG:
print("Anomaly at chapter {} ({} matches, chose {})".format(i[0][3], len(ll), i[0][2]))
del i[1:]
sc = i[0]
continue
i[0] = ll[0]
sc = i[0]
del i[1:]
self.chapters = [i[0] for i in self.chapters]
upperRange = len(self.chapters)
# which ones do we want?
if (not self.auto):
for n,c in enumerate(self.chapters):
print("{:03d}. {}".format(n+1, c[1].encode('utf-8')))
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if ( lowerRange == upperRange):
raise self.NoUpdates
for i in range (lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
"""
Parses list of chapters and URLs associated with each one for the given manga and site.
"""
print("Beginning MangaFox check: %s" % self.manga)
# jump straight to expected URL and test if manga removed
url = "http://mangafox.me/manga/%s/" % self.fixFormatting(self.manga)
if self.verbose_FLAG:
print(url)
source, redirectURL = getSourceCode(url, self.proxy, True)
if redirectURL != url or source is None or "the page you have requested cannot be found" in source:
# Could not find the manga page by guessing
# Use the website search
url = "http://mangafox.me/search.php?name_method=bw&name=%s&is_completed=&advopts=1" % "+".join(
self.manga.split()
)
if self.verbose_FLAG:
print(url)
try:
source = getSourceCode(url, self.proxy)
seriesResults = []
if source is not None:
seriesResults = MangaFox.re_getSeries.findall(source)
if 0 == len(seriesResults):
url = "http://mangafox.me/search.php?name_method=cw&name=%s&is_completed=&advopts=1" % "+".join(
self.manga.split()
)
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if source is not None:
seriesResults = MangaFox.re_getSeries.findall(source)
# 0 results
except AttributeError:
raise self.MangaNotFound("It doesn't exist, or cannot be resolved by autocorrect.")
else:
keyword = self.selectFromResults(seriesResults)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
url = "http://mangafox.me/manga/%s/" % keyword
if self.verbose_FLAG:
print("URL: %s" % url)
source = getSourceCode(url, self.proxy)
if source is None:
raise self.MangaNotFound("Search Failed to find Manga.")
else:
# The Guess worked
keyword = self.fixFormatting(self.manga)
if self.verbose_FLAG:
print("Keyword: %s" % keyword)
if "it is not available in Manga Fox." in source:
raise self.MangaNotFound("It has been removed.")
# that's nice of them
# url = 'http://mangafox.me/cache/manga/%s/chapters.js' % keyword
# source = getSourceCode(url, self.proxy)
# chapters is a 2-tuple
# chapters[0] contains the chapter URL
# chapters[1] contains the chapter title
isChapterOnly = False
# can't pre-compile this because relies on class name
re_getChapters = re.compile('a href="http://.*?mangafox.*?/manga/%s/(v[\d]+)/(c[\d]+)/[^"]*?" title' % keyword)
self.chapters = re_getChapters.findall(source)
if not self.chapters:
if self.verbose_FLAG:
print("Trying chapter only regex")
isChapterOnly = True
re_getChapters = re.compile('a href="http://.*?mangafox.*?/manga/%s/(c[\d]+)/[^"]*?" title' % keyword)
self.chapters = re_getChapters.findall(source)
self.chapters.reverse()
# code used to both fix URL from relative to absolute as well as verify last downloaded chapter for XML component
lowerRange = 0
if isChapterOnly:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s" % self.chapters[i])
if not self.auto:
print("(%i) %s" % (i + 1, self.chapters[i]))
else:
if self.lastDownloaded == self.chapters[i]:
lowerRange = i + 1
self.chapters[i] = (
"http://mangafox.me/manga/%s/%s" % (keyword, self.chapters[i]),
self.chapters[i],
self.chapters[i],
)
else:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s %s" % (self.chapters[i][0], self.chapters[i][1]))
self.chapters[i] = (
"http://mangafox.me/manga/%s/%s/%s" % (keyword, self.chapters[i][0], self.chapters[i][1]),
self.chapters[i][0] + "." + self.chapters[i][1],
self.chapters[i][1],
)
if not self.auto:
print("(%i) %s" % (i + 1, self.chapters[i][1]))
else:
if self.lastDownloaded == self.chapters[i][1]:
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
# which ones do we want?
if not self.auto:
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if lowerRange == upperRange:
raise self.NoUpdates
for i in range(lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
"""
Parses list of chapters and URLs associated with each one for the given manga and site.
"""
print('Beginning MangaHere check: %s' % self.manga)
# jump straight to expected URL and test if manga removed
url = 'http://www.mangahere.com/manga/%s/' % self.fixFormatting( self.manga )
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if (source is None or 'the page you have requested can' in source):
# do a 'begins-with' search, then a 'contains' search
url = 'http://www.mangahere.com/search.php?name=%s' % '+'.join(self.manga.split())
if self.verbose_FLAG:
print(url)
try:
source = getSourceCode(url, self.proxy)
if('Sorry you have just searched, please try 5 seconds later.' in source):
print('Searched too soon, waiting 5 seconds...')
time.sleep(5)
seriesResults = MangaHere.re_getSeries.findall(source)
seriesResults = []
if source is not None:
seriesResults = MangaHere.re_getSeries.findall(source)
if (0 == len(seriesResults) ):
url = 'http://www.mangahere.com/search.php?name=%s' % '+'.join(self.manga.split())
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
if source is not None:
seriesResults = MangaHere.re_getSeries.findall(source)
# 0 results
except AttributeError:
raise self.MangaNotFound('It doesn\'t exist, or cannot be resolved by autocorrect.')
else:
keyword = self.selectFromResults(seriesResults)
if self.verbose_FLAG:
print ("Keyword: %s" % keyword)
url = 'http://www.mangahere.com/manga/%s/' % keyword
if self.verbose_FLAG:
print(url)
source = getSourceCode(url, self.proxy)
else:
# The Guess worked
keyword = self.fixFormatting( self.manga )
if self.verbose_FLAG:
print ("Keyword: %s" % keyword)
# other check for manga removal if our initial guess for the name was wrong
if('it is not available in.' in source):
raise self.MangaNotFound('It has been removed.')
# that's nice of them
#url = 'http://www.mangahere.com/cache/manga/%s/chapters.js' % keyword
#source = getSourceCode(url, self.proxy)
# chapters is a 2-tuple
# chapters[0] contains the chapter URL
# chapters[1] contains the chapter title
isChapterOnly = False
# can't pre-compile this because relies on class name
re_getChapters = re.compile('a.*?href="http://.*?mangahere.*?/manga/%s/(v[\d]+)/(c[\d]+(\.[\d]+)?)/[^"]*?"' % keyword)
self.chapters = re_getChapters.findall(source)
if not self.chapters:
if self.verbose_FLAG:
print ("Trying chapter only regex")
isChapterOnly = True
re_getChapters = re.compile('a.*?href="http://.*?mangahere.*?/manga/%s/(c[\d]+(\.[\d]+)?)/[^"]*?"' % keyword)
self.chapters = re_getChapters.findall(source)
#Sort chapters by volume and chapter number. Needed because next chapter isn't always accurate.
self.chapters = sorted(self.chapters, cmp=self.chapter_compare)
# code used to both fix URL from relative to absolute as well as verify last downloaded chapter for XML component
lowerRange = 0
if isChapterOnly:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s" % self.chapters[i][0])
if (self.auto):
if (self.lastDownloaded == self.chapters[i][0]):
lowerRange = i + 1
self.chapters[i] = ('http://www.mangahere.com/manga/%s/%s' % (keyword, self.chapters[i][0]), self.chapters[i][0], self.chapters[i][0])
else:
for i in range(0, len(self.chapters)):
if self.verbose_FLAG:
print("%s %s" % (self.chapters[i][0], self.chapters[i][1]))
self.chapters[i] = ('http://www.mangahere.com/manga/%s/%s/%s' % (keyword, self.chapters[i][0], self.chapters[i][1]), self.chapters[i][0] + "." + self.chapters[i][1], self.chapters[i][1])
if (self.auto):
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
# Validate whether the last chapter is a
if (self.verbose_FLAG):
print(self.chapters[upperRange - 1])
print("Validating chapter: %s" % self.chapters[upperRange - 1][0])
source = getSourceCode(self.chapters[upperRange - 1][0], self.proxy)
if ('not available yet' in source) or ('Sorry, the page you have requested can’t be found' in source):
# If the last chapter is not available remove it from the list
del self.chapters[upperRange - 1]
upperRange = upperRange - 1;
# which ones do we want?
if (not self.auto):
for i in range(0, upperRange):
if isChapterOnly:
print('(%i) %s' % (i + 1, self.chapters[i][0]))
else:
print('(%i) %s' % (i + 1, self.chapters[i][1]))
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if ( lowerRange == upperRange):
raise self.NoUpdates
for i in range (lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def parseSite(self):
"""
Parses list of chapters and URLs associated with each one for the given manga and site.
"""
print('Beginning MangaFox check: %s' % self.manga)
# jump straight to expected URL and test if manga removed
url = 'http://www.mangafox.com/manga/%s/' % self.fixFormatting( self.manga )
if self.verbose_FLAG:
print(url)
source = getSourceCode(url)
if('it is not available in Manga Fox.' in source):
raise self.MangaNotFound('It has been removed.')
# do a 'begins-with' search, then a 'contains' search
url = 'http://www.mangafox.com/search.php?name_method=bw&name=%s' % '+'.join(self.manga.split())
if self.verbose_FLAG:
print(url)
try:
source = getSourceCode(url)
seriesResults = MangaFox.re_getSeries.findall(source)
if (0 == len(seriesResults) ):
url = 'http://www.mangafox.com/search.php?name=%s' % '+'.join(self.manga.split())
if self.verbose_FLAG:
print(url)
source = getSourceCode(url)
seriesResults = MangaFox.re_getSeries.findall(source)
# 0 results
except AttributeError:
raise self.MangaNotFound('It doesn\'t exist, or cannot be resolved by autocorrect.')
else:
keyword = self.selectFromResults(seriesResults)
if self.verbose_FLAG:
print ("Keyword: %s" % keyword)
url = 'http://www.mangafox.com/manga/%s/' % keyword
source = getSourceCode(url)
# other check for manga removal if our initial guess for the name was wrong
if('it is not available in Manga Fox.' in source):
raise self.MangaNotFound('It has been removed.')
# that's nice of them
#url = 'http://www.mangafox.com/cache/manga/%s/chapters.js' % keyword
#source = getSourceCode(url)
# chapters is a 2-tuple
# chapters[0] contains the chapter URL
# chapters[1] contains the chapter title
# can't pre-compile this because relies on class name
re_getChapters = re.compile('a href="http://.*?mangafox.*?/manga/%s/(v[\d]+)/(c[\d]+)/[^"]*?" title' % keyword)
self.chapters = re_getChapters.findall(source)
self.chapters.reverse()
# code used to both fix URL from relative to absolute as well as verify last downloaded chapter for XML component
lowerRange = 0
for i in range(0, len(self.chapters)):
#print("%s %s" % (self.chapters[i][0], self.chapters[i][1]))
self.chapters[i] = ('http://www.mangafox.com/manga/%s/%s/%s' % (keyword, self.chapters[i][0], self.chapters[i][1]), self.chapters[i][0] + "." + self.chapters[i][1], self.chapters[i][1])
if (not self.auto):
print('(%i) %s' % (i + 1, self.chapters[i][1]))
else:
if (self.lastDownloaded == self.chapters[i][1]):
lowerRange = i + 1
# this might need to be len(self.chapters) + 1, I'm unsure as to whether python adds +1 to i after the loop or not
upperRange = len(self.chapters)
# which ones do we want?
if (not self.auto):
self.chapters_to_download = self.selectChapters(self.chapters)
# XML component
else:
if ( lowerRange == upperRange):
raise self.NoUpdates
for i in range (lowerRange, upperRange):
self.chapters_to_download.append(i)
return
def get_next_url(self, c):
s = getSourceCode(c, self.proxy)
soup = BeautifulSoup(s)
l = soup.find("img", title="Next Chapter").parent
return l['href']
