def fds(self):
self.subject = 'feminisme'
# self.title = 'fds '+ findTextBetweenTag (self.text, 'title').lower()
self.title = 'fds ' + self.title
self.text = findTextBetweenTag(self.text, 'article')
self.author = findTextBetweenTag(self.text, 'li')
d = self.index('<article>') + 9
d = self.index('<', d)
self.text = self.text[d:]
self.replace('<div>')
self.replace('</div>')
def unisciel(self, subject):
self.subject = 'cours'
self.author = 'unisciel'
self.text = findTextBetweenTag(self.text, 'body')
self.cleanWeb()
self.delScript()
d = self.index('<td>') + 4
f = self.index('</td>', d)
self.title = self.text[d:f].lower()
d = self.index('<p>')
f = self.rindex('</p>') + 4
self.text = self.text[d:f]
self.replace('<div>')
self.replace('</div>')
self.replace('<img', '</p><img')
self.replace("png'>", "png'><p>")
self.replace('<p><p>', '<p>')
self.replace('</p></p>', '</p>')
self.replace('<p>', '</p><p>')
self.replace('</p>', '</p><p>')
self.replace('<p></p>')
self.replace('<p><p>', '<p>')
self.replace('<p><img', '<img')
self.replace("png'></p>", "png'>")
self.text = self.text[4:-3]
self.replace('../res/', 'bv-' + subject + '/')
self.replace("</p><img src='bv-" + subject + "/apprendre_ch2_01.png'><p>",
' <b>ADP +P --> ATP</b> ')
self.replace(
"</p><img src='bv-" + subject + "/apprendre_ch2_01_1.png'><p>",
' <b>ATP --> ADP +P</b> ')
self.styles.append('unisciel.css')
def aooo(self, subject=None):
if 'This work could have adult content. If you proceed you have agreed that you are willing to see such content' in self.text:
print('fichier protégé', self.title)
return
self.cleanWeb()
self.replace('<br>', '</p><p>')
self.text = findTextBetweenTag(self.text, 'body')
# le titre
d = self.index('<h2>') + 4
f = self.index('</h2>', d)
self.title = self.text[d:f]
self.title = self.title.strip()
self.title = self.title.strip('.')
# l'auteur et sa page
d = self.index("<a href='/users/", f) + 9
f = self.index("'", d)
self.autlink = self.text[d:f]
d = self.index('>', d) + 1
f = self.index('</a>', d)
self.author = self.text[d:f]
# le sujet
self.findSubject(subject)
if self.subject == 'histoire':
d = self.index('Additional Tags:<ul>') + 24
d = self.index('>', d) + 1
f = self.index('<', d)
self.subject = self.text[d:f]
# le texte ne compte qu'un seul chapître
d = self.index('<h3>Work Text:</h3>') + 19
# le texte compte plusieurs chapîtres
if d == 18: d = self.index("<h3><a href='/works/")
f = self.rindex('<h3>Actions</h3>')
self.text = self.text[d:f]
self.replace('<div>')
self.replace('</div>')
self.replace('<h3>Chapter Text</h3>')
if self.contain("<h3><a href='/works/"):
chapters = List()
chapters.fromText("<h3><a href='/works/", self.text)
chapterRange = chapters.range(1)
for c in chapterRange:
d = chapters[c].find('>') + 1
chapters[c] = chapters[c][d:]
self.text = '<h2>'.join(chapters)
self.replace('</a></h3>', '</h2>')
if self.contain('<h2>Chapter ') and not self.contain('</h2>'):
chapters = List()
chapters.fromText('<h2>Chapter ', self.text)
chapterRange = chapters.range(1)
for c in chapterRange:
d = chapters[c].find('</a>: ') + 6
chapters[c] = chapters[c][d:]
chapters[c] = chapters[c].replace('</h3>', '</h2>', 1)
self.text = '<h2>'.join(chapters)
# nettoyer le texte
if self.contain('<h3>Notes:</h3>'):
halfText = self.length() / 2
d = self.index('<h3>Notes:</h3>')
if d > halfText: self.text = self.text[:d]
self.usePlaceholders()
def ficAooo(self, subject=None):
if 'This work could have adult content. If you proceed you have agreed that you are willing to see such content' in self.text:
print('fichier protégé', self.title)
return
self.cleanWeb()
self.replace('<br>', '</p><p>')
self.text = findTextBetweenTag(self.text, 'body')
# le titre
d = self.index('<h2>') + 4
f = self.index('</h2>', d)
self.title = self.text[d:f]
self.title = self.title.strip()
self.title = self.title.strip('.')
self.ficAoooCommon()