def url_encode(query, clean=True, doseq=True, **kw):
query = web.dictadd(query, kw)
if clean is True:
for q, v in query.items():
if not v:
del query[q]
return urllib.urlencode(query, doseq)
def __init__(self, from_address, to_address, subject, message, headers=None, **kw):
def listify(x):
if not isinstance(x, list):
return [safestr(x)]
else:
return [safestr(a) for a in x]
subject = safestr(subject)
message = safestr(message)
from_address = safestr(from_address)
to_address = listify(to_address)
cc = listify(kw.get('cc', []))
bcc = listify(kw.get('bcc', []))
recipients = to_address + cc + bcc
import email.Utils
self.from_address = email.Utils.parseaddr(from_address)[1]
self.recipients = [email.Utils.parseaddr(r)[1] for r in recipients]
self.headers = dictadd({
'From': from_address,
'To': ", ".join(to_address),
'Subject': subject
}, headers or {})
if cc:
self.headers['Cc'] = ", ".join(cc)
self.message = self.new_message()
self.message.add_header("Content-Transfer-Encoding", "7bit")
self.message.add_header("Content-Disposition", "inline")
self.message.add_header("MIME-Version", "1.0")
self.message.set_payload(message, 'utf-8')
self.multipart = False
def url_encode(query, clean=True, doseq=True, **kw):
query = web.dictadd(query, kw)
if clean is True:
for q, v in query.items():
if not v:
del query[q]
return urllib.urlencode(query, doseq)
def init_webpy_app(self, mapping=(), fvars={}, autoreload=None):
"""Initializes webpy app which delegate requests based on path."""
# the default url mapping
mapping = mapping + MAPPING
# not sure why this is needed
fvars = web.dictadd(locals(), fvars)
# create webapy app with these settings
super(CloudMiningApp, self).__init__(mapping, fvars, autoreload)
def init_webpy_app(self, mapping=(), fvars={}, autoreload=None):
"""Initializes webpy app which delegate requests based on path."""
# the default url mapping
mapping = mapping + MAPPING
# not sure why this is needed
fvars = web.dictadd(locals(), fvars)
# create webapy app with these settings
super(CloudMiningApp, self).__init__(mapping, fvars, autoreload)
def url_encode2(inputs, clean=True, doseq=True, **kw):
inputs = web.dictadd(inputs, kw)
if clean is True:
for q, v in inputs.items():
if not v:
del inputs[q]
if isinstance(v, unicode):
inputs[q] = v.encode('utf-8')
return urllib.urlencode(inputs, doseq)
def url_encode2(inputs, clean=True, doseq=True, **kw):
inputs = web.dictadd(inputs, kw)
if clean is True:
for q, v in inputs.items():
if not v:
del inputs[q]
if isinstance(v, unicode):
inputs[q] = v.encode('utf-8')
return urllib.urlencode(inputs, doseq)
def __init__(self, db, flash, **settings):
self._db = db
self._flash = flash
self.config = web.storage(web.dictadd(DEFAULT_SETTINGS, settings))
hashtype = self.config.get('hash')
try:
if hashtype == 'sha512':
self.hash = hash_sha512
elif hashtype == 'sha1':
self.hash = hash_sha1
elif hashtype == 'bcrypt':
self.hash = hash_bcrypt
else:
raise HashError("Hash type must be sha512, sha1 or bcrypt")
except ImportError:
raise HashError('Hash type %s not available' % (hash,))
def process_doc(self, doc):
"""Processes one document.
Should be called only after initializing self.authors and self.works.
"""
w = self.get_work(doc)
def subject(name, prefix):
# handle bad subjects loaded earlier.
if isinstance(name, dict):
if 'value' in name:
name = name['value']
elif 'key' in name:
name = name['key'].split("/")[-1].replace("_", " ")
else:
return {}
return {
"name": name,
"url": "https://openlibrary.org/subjects/%s%s" % (prefix, name.lower().replace(" ", "_"))
}
def get_subjects(name, prefix):
return [subject(s, prefix) for s in w.get(name, '')]
def get_value(v):
if isinstance(v, dict):
return v.get('value', '')
else:
return v
def format_excerpt(e):
return {
"text": get_value(e.get("excerpt", {})),
"comment": e.get("comment", "")
}
def format_table_of_contents(toc):
# after openlibrary.plugins.upstream.models.get_table_of_contents
def row(r):
if isinstance(r, six.string_types):
level = 0
label = ""
title = r
pagenum = ""
else:
level = h.safeint(r.get('level', '0'), 0)
label = r.get('label', '')
title = r.get('title', '')
pagenum = r.get('pagenum', '')
r = dict(level=level, label=label, title=title, pagenum=pagenum)
return r
d = [row(r) for r in toc]
return [row for row in d if any(row.values())]
d = {
"url": get_url(doc),
"key": doc['key'],
"title": doc.get("title", ""),
"subtitle": doc.get("subtitle", ""),
"authors": self.get_authors(w),
"number_of_pages": doc.get("number_of_pages", ""),
"pagination": doc.get("pagination", ""),
"weight": doc.get("weight", ""),
"by_statement": doc.get("by_statement", ""),
'identifiers': web.dictadd(doc.get('identifiers', {}), {
'isbn_10': doc.get('isbn_10', []),
'isbn_13': doc.get('isbn_13', []),
'lccn': doc.get('lccn', []),
'oclc': doc.get('oclc_numbers', []),
'openlibrary': [doc['key'].split("/")[-1]]
}),
'classifications': web.dictadd(doc.get('classifications', {}), {
'lc_classifications': doc.get('lc_classifications', []),
'dewey_decimal_class': doc.get('dewey_decimal_class', [])
}),
"publishers": [{"name": p} for p in doc.get("publishers", "")],
"publish_places": [{"name": p} for p in doc.get("publish_places", "")],
"publish_date": doc.get("publish_date"),
"subjects": get_subjects("subjects", ""),
"subject_places": get_subjects("subject_places", "place:"),
"subject_people": get_subjects("subject_people", "person:"),
"subject_times": get_subjects("subject_times", "time:"),
"excerpts": [format_excerpt(e) for e in w.get("excerpts", [])],
"notes": get_value(doc.get("notes", "")),
"table_of_contents": format_table_of_contents(doc.get("table_of_contents", [])),
"links": [dict(title=link.get("title"), url=link['url']) for link in w.get('links', '') if link.get('url')],
}
for fs in [doc.get("first_sentence"), w.get('first_sentence')]:
if fs:
e = {
"text": get_value(fs),
"comment": "",
"first_sentence": True
}
d['excerpts'].insert(0, e)
break
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "https://archive.org/details/" + itemid,
"availability": availability,
"formats": {}
}
prefix = "https://archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "https://archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
}
}
elif availability == "borrow":
d['borrow_url'] = u"https://openlibrary.org%s/%s/borrow" % (doc['key'], h.urlsafe(doc.get("title", "untitled")))
loanstatus = web.ctx.site.store.get('ebooks/' + doc['ocaid'], {'borrowed': 'false'})
d['checkedout'] = (loanstatus['borrowed'] == 'true')
return d
if doc.get("ocaid"):
d['ebooks'] = [ebook(doc)]
if doc.get('covers'):
cover_id = doc['covers'][0]
d['cover'] = {
"small": "https://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "https://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "https://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
d['identifiers'] = trim(d['identifiers'])
d['classifications'] = trim(d['classifications'])
return trim(d)
def process_doc(self, doc):
"""Processes one document.
Should be called only after initializing self.authors and self.works.
"""
w = self.get_work(doc)
def subject(name, prefix):
# handle bad subjects loaded earlier.
if isinstance(name, dict):
if 'value' in name:
name = name['value']
elif 'key' in name:
name = name['key'].split("/")[-1].replace("_", " ")
else:
return {}
return {
"name": name,
"url": "http://openlibrary.org/subjects/%s%s" % (prefix, name.lower().replace(" ", "_"))
}
def get_subjects(name, prefix):
return [subject(s, prefix) for s in w.get(name, '')]
def get_value(v):
if isinstance(v, dict):
return v.get('value', '')
else:
return v
def format_excerpt(e):
return {
"text": get_value(e.get("excerpt", {})),
"comment": e.get("comment", "")
}
d = {
"url": get_url(doc),
"key": doc['key'],
"title": doc.get("title", ""),
"subtitle": doc.get("subtitle", ""),
"authors": self.get_authors(w),
"number_of_pages": doc.get("number_of_pages", ""),
"pagination": doc.get("pagination", ""),
"weight": doc.get("weight", ""),
"by_statement": doc.get("by_statement", ""),
'identifiers': web.dictadd(doc.get('identifiers', {}), {
'isbn_10': doc.get('isbn_10', []),
'isbn_13': doc.get('isbn_13', []),
'lccn': doc.get('lccn', []),
'oclc': doc.get('oclc_numbers', []),
'openlibrary': [doc['key'].split("/")[-1]]
}),
'classifications': web.dictadd(doc.get('classifications', {}), {
'lc_classifications': doc.get('lc_classifications', []),
'dewey_decimal_class': doc.get('dewey_decimal_class', [])
}),
"publishers": [{"name": p} for p in doc.get("publishers", "")],
"publish_places": [{"name": p} for p in doc.get("publish_places", "")],
"publish_date": doc.get("publish_date"),
"subjects": get_subjects("subjects", ""),
"subject_places": get_subjects("subject_places", "place:"),
"subject_people": get_subjects("subject_people", "person:"),
"subject_times": get_subjects("subject_times", "time:"),
"excerpts": [format_excerpt(e) for e in w.get("excerpts", [])],
"links": [dict(title=link.get("title"), url=link['url']) for link in w.get('links', '') if link.get('url')],
}
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "http://www.archive.org/details/" + itemid,
"availability": availability
}
prefix = "http://www.archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "http://www.archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
},
"djvu": {
"url": prefix + ".djvu",
"permission": "open"
}
}
elif availability == "borrow":
d['borrow_url'] = u"http://openlibrary.org%s/%s/borrow" % (doc['key'], h.urlsafe(doc.get("title", "untitled")))
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
else:
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
return d
if doc.get("ocaid"):
d['ebooks'] = [ebook(doc)]
if doc.get('covers'):
cover_id = doc['covers'][0]
d['cover'] = {
"small": "http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
d['identifiers'] = trim(d['identifiers'])
d['classifications'] = trim(d['classifications'])
return trim(d)
def process_doc(self, doc):
"""Processes one document.
Should be called only after initializing self.authors and self.works.
"""
w = self.get_work(doc)
def subject(name, prefix):
# handle bad subjects loaded earlier.
if isinstance(name, dict):
if 'value' in name:
name = name['value']
elif 'key' in name:
name = name['key'].split("/")[-1].replace("_", " ")
else:
return {}
return {
"name": name,
"url": "https://openlibrary.org/subjects/%s%s" % (prefix, name.lower().replace(" ", "_"))
}
def get_subjects(name, prefix):
return [subject(s, prefix) for s in w.get(name, '')]
def get_value(v):
if isinstance(v, dict):
return v.get('value', '')
else:
return v
def format_excerpt(e):
return {
"text": get_value(e.get("excerpt", {})),
"comment": e.get("comment", "")
}
def format_table_of_contents(toc):
# after openlibrary.plugins.upstream.models.get_table_of_contents
def row(r):
if isinstance(r, basestring):
level = 0
label = ""
title = r
pagenum = ""
else:
level = h.safeint(r.get('level', '0'), 0)
label = r.get('label', '')
title = r.get('title', '')
pagenum = r.get('pagenum', '')
r = dict(level=level, label=label, title=title, pagenum=pagenum)
return r
d = [row(r) for r in toc]
return [row for row in d if any(row.values())]
d = {
"url": get_url(doc),
"key": doc['key'],
"title": doc.get("title", ""),
"subtitle": doc.get("subtitle", ""),
"authors": self.get_authors(w),
"number_of_pages": doc.get("number_of_pages", ""),
"pagination": doc.get("pagination", ""),
"weight": doc.get("weight", ""),
"by_statement": doc.get("by_statement", ""),
'identifiers': web.dictadd(doc.get('identifiers', {}), {
'isbn_10': doc.get('isbn_10', []),
'isbn_13': doc.get('isbn_13', []),
'lccn': doc.get('lccn', []),
'oclc': doc.get('oclc_numbers', []),
'openlibrary': [doc['key'].split("/")[-1]]
}),
'classifications': web.dictadd(doc.get('classifications', {}), {
'lc_classifications': doc.get('lc_classifications', []),
'dewey_decimal_class': doc.get('dewey_decimal_class', [])
}),
"publishers": [{"name": p} for p in doc.get("publishers", "")],
"publish_places": [{"name": p} for p in doc.get("publish_places", "")],
"publish_date": doc.get("publish_date"),
"subjects": get_subjects("subjects", ""),
"subject_places": get_subjects("subject_places", "place:"),
"subject_people": get_subjects("subject_people", "person:"),
"subject_times": get_subjects("subject_times", "time:"),
"excerpts": [format_excerpt(e) for e in w.get("excerpts", [])],
"notes": get_value(doc.get("notes", "")),
"table_of_contents": format_table_of_contents(doc.get("table_of_contents", [])),
"links": [dict(title=link.get("title"), url=link['url']) for link in w.get('links', '') if link.get('url')],
}
for fs in [doc.get("first_sentence"), w.get('first_sentence')]:
if fs:
e = {
"text": get_value(fs),
"comment": "",
"first_sentence": True
}
d['excerpts'].insert(0, e)
break
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "https://archive.org/details/" + itemid,
"availability": availability,
"formats": {}
}
prefix = "https://archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "https://archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
}
}
elif availability == "borrow":
d['borrow_url'] = u"https://openlibrary.org%s/%s/borrow" % (doc['key'], h.urlsafe(doc.get("title", "untitled")))
loanstatus = web.ctx.site.store.get('ebooks/' + doc['ocaid'], {'borrowed': 'false'})
d['checkedout'] = (loanstatus['borrowed'] == 'true')
return d
if doc.get("ocaid"):
d['ebooks'] = [ebook(doc)]
if doc.get('covers'):
cover_id = doc['covers'][0]
d['cover'] = {
"small": "https://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "https://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "https://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
d['identifiers'] = trim(d['identifiers'])
d['classifications'] = trim(d['classifications'])
return trim(d)
def process_doc(self, doc):
"""Processes one document.
Should be called only after initializing self.authors and self.works.
"""
w = self.get_work(doc)
def subject(name, prefix):
# handle bad subjects loaded earlier.
if isinstance(name, dict):
if 'value' in name:
name = name['value']
elif 'key' in name:
name = name['key'].split("/")[-1].replace("_", " ")
else:
return {}
return {
"name": name,
"url": "http://openlibrary.org/subjects/%s%s" % (prefix, name.lower().replace(" ", "_"))
}
def get_subjects(name, prefix):
return [subject(s, prefix) for s in w.get(name, '')]
def get_value(v):
if isinstance(v, dict):
return v.get('value', '')
else:
return v
def format_excerpt(e):
return {
"text": get_value(e.get("excerpt", {})),
"comment": e.get("comment", "")
}
d = {
"url": get_url(doc),
"title": doc.get("title", ""),
"subtitle": doc.get("subtitle", ""),
"authors": self.get_authors(w),
"number_of_pages": doc.get("number_of_pages", ""),
"weight": doc.get("weight", ""),
'identifiers': web.dictadd(doc.get('identifiers', {}), {
'isbn_10': doc.get('isbn_10', []),
'isbn_13': doc.get('isbn_13', []),
'lccn': doc.get('lccn', []),
'oclc': doc.get('oclc_numbers', []),
}),
'classifications': web.dictadd(doc.get('classifications', {}), {
'lc_classifications': doc.get('lc_classifications', []),
'dewey_decimal_class': doc.get('dewey_decimal_class', [])
}),
"publishers": [{"name": p} for p in doc.get("publishers", "")],
"publish_places": [{"name": p} for p in doc.get("publish_places", "")],
"publish_date": doc.get("publish_date"),
"subjects": get_subjects("subjects", ""),
"subject_places": get_subjects("subject_places", "place:"),
"subject_people": get_subjects("subject_people", "person:"),
"subject_times": get_subjects("subject_times", "time:"),
"excerpts": [format_excerpt(e) for e in w.get("excerpts", [])],
"links": [dict(title=link.get("title"), url=link['url']) for link in w.get('links', '') if link.get('url')],
}
if doc.get("ocaid"):
d['ebooks'] = [{"preview_url": "http://www.archive.org/details/" + doc['ocaid']}]
if doc.get('covers'):
cover_id = doc['covers'][0]
d['cover'] = {
"small": "http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
d['identifiers'] = trim(d['identifiers'])
d['classifications'] = trim(d['classifications'])
return trim(d)
