def _get_html(url):
user_agent = random_user_agent()
try:
return session.get(url, headers={'User-Agent': user_agent}).text
except Exception as e:
return session.get(url,
verify=False,
headers={
'User-Agent': user_agent
}).text
def get_author(author_id):
"""
Args:
author_id:
Returns:
"""
url = Librivox.authors_url % ("id=" + str(author_id), )
json_data = session.get(url).json()["authors"]
return BookAuthor(from_data=json_data[0])
def scrap_all_audiobooks(cls, limit=2000, offset=0):
"""
Generator, yields LibrivoxAudioBook objects
Args:
limit:
offset:
"""
url = cls.base_url % \
("limit=" + str(limit) + "offset=" + str(offset) + "&extended=1")
json_data = session.get(url).json()['books']
for k in json_data:
yield LibrivoxAudioBook(from_data=json_data[k])
def get_audiobook(book_id):
"""
Args:
book_id:
Returns:
LibrivoxAudioBook
"""
url = Librivox.base_url % ("id=" + str(book_id), )
json_data = session.get(url).json()['books']
return LibrivoxAudioBook(from_data=json_data[0])
def _request(url, params=None, user_agent=None):
params = params or {}
try:
user_agent = user_agent or random_user_agent()
response = session.get(url, params=params,
headers={
'User-Agent': user_agent,
"Accept-Language": "en-US,en;q=0.5"
})
except Exception as e:
print(e)
raise
return response.text
def search_audiobooks(cls,
since=None,
author=None,
title=None,
tag=None,
limit=25):
"""
Args:
since: a UNIX timestamp; returns all projects cataloged since that time
author: all records by that author last name
title: all matching titles
tag: all projects of the matching tag
Returns:
list : list of LibrivoxAudioBook objects
"""
searchterm = []
if limit:
# TODO validate
searchterm.append("limit=" + str(limit))
if since:
# TODO validate
searchterm.append("since=" + since)
if author:
searchterm.append("author=" + author)
if title:
searchterm.append("title=" + title)
if tag:
# TODO validate
searchterm.append("tag=" + tag)
if not searchterm:
raise TypeError
searchterm = "&".join(searchterm)
url = cls.base_url % (searchterm, )
json_data = session.get(url).json()
if "error" in json_data:
return []
return [LibrivoxAudioBook(from_data=a) for a in json_data["books"]]
def get_author(cls, author_id):
url = cls.authors_url % ("id=" + str(author_id), )
json_data = session.get(url).json()["authors"]
return BookAuthor(from_data=json_data[0])
def get_audiobook(cls, book_id):
url = cls.base_url % ("id=" + str(book_id), )
json_data = session.get(url).json()['books']
return LibrivoxAudioBook(from_data=json_data[0])
