def parse(self, soup):
"""
:return: List of items with their details
"""
# Adds title
rdata = self.scraper.archive_list.get(self.comic_id)
# Parse the items here and return the content to be added to the db
comic_raw = soup.find(id='cc-comic')
img_src = comic_raw['src']
comic_filename = '{base}/{year}/{month}/{name}{ext}'\
.format(base=self.scraper.BASE_SAVE_DIR,
year=rdata['posted_at'].year,
month=rdata['posted_at'].month,
name=str(rdata['posted_at']),
ext=cutil.get_file_ext(img_src))
rdata.update({
'time_collected':
cutil.get_datetime(),
'file_path':
self.web.download(img_src, comic_filename).replace(
self.scraper.BASE_DATA_DIR + os.path.sep, ''),
'alt':
comic_raw['title']
})
return rdata
def log_last_scraped(self):
try:
setting = db_session.query(Setting).filter(Setting.bit == 0).one()
setting.comic_last_ran = cutil.get_datetime()
db_session.add(setting)
db_session.commit()
except:
logger.exception("Problem logging last comic scraped")
def parse_book(self, content):
"""
:return: List of items with their details
"""
cover_source = content.find('img', {'itemprop': 'image'})['src'].strip()
try:
subtitle = content.find('h3').getText().strip()
except AttributeError:
subtitle = None
try:
file_source = content.find('a', {'href': re.compile('http://filepi.com')})['href']
except (AttributeError, TypeError):
file_source = None
parsed_data = {'book_id': self.book_id,
'file_location': None,
'file_cover_location': None,
'file_cover_source': self.web.scraper.BASE_URL + cover_source,
'description': content.find('span', {'itemprop': 'description'}).getText().strip(),
'file_source': file_source,
'format': content.find(attrs={'itemprop': 'bookFormat'}).getText().strip().lower(),
'isbn': content.find(attrs={'itemprop': 'isbn'}).getText().strip(),
'language': content.find(attrs={'itemprop': 'inLanguage'}).getText().strip(),
'pages': content.find(attrs={'itemprop': 'numberOfPages'}).getText().strip(),
'publisher': content.find(attrs={'itemprop': 'publisher'}).getText().strip(),
'title': content.find('h1', {'itemprop': 'name'}).getText().strip(),
'subtitle': subtitle,
'year': content.find(attrs={'itemprop': 'datePublished'}).getText().strip(),
'author': content.find(attrs={'itemprop': 'author'}).getText().strip(),
'time_collected': cutil.get_datetime(),
}
# Download book
base_filename = '{last_nums}/{book_id}/{book_id}'\
.format(last_nums=self.book_id[-2:], book_id=self.book_id)
book_filename = '{base_filename}_book.{ext}'.format(base_filename=base_filename,
ext=parsed_data.get('format'))
cover_ext = cutil.get_file_ext(parsed_data.get('file_cover_source'))
book_cover_filename = '{base_filename}_cover{ext}'.format(base_filename=base_filename,
ext=cover_ext)
parsed_data['file_cover_location'] = self.web.download(parsed_data.get('file_cover_source'),
book_cover_filename)
header = {'Referer': self.web.scraper.BASE_URL}
if parsed_data.get('file_source') is not None:
parsed_data['file_location'] = self.web.download(parsed_data.get('file_source'),
book_filename,
header=header)
return parsed_data
def log_last_scraped(self):
try:
try:
last_comic_id = min(self.comic_ids) - 1
except ValueError:
last_comic_id = self.max_id
setting = db_session.query(Setting).filter(Setting.bit == 0).one()
setting.comic_last_id = last_comic_id
setting.comic_last_ran = cutil.get_datetime()
db_session.add(setting)
db_session.commit()
except:
logger.exception("Problem logging last comic scraped")
def log_last_scraped(self):
try:
try:
last_book_id = db_session.query(Book).order_by(Book.book_id.desc()).first()
if last_book_id is not None:
setting = db_session.query(Setting).filter(Setting.bit == 0).one()
setting.book_last_id = last_book_id.book_id
setting.book_last_ran = cutil.get_datetime()
db_session.add(setting)
db_session.commit()
except NoResultFound:
# If there is no raw data then no books were collected
pass
except:
logger.exception("Problem logging last book scraped")
def log_last_scraped(self):
try:
try:
last_book_id = db_session.query(Book).order_by(
Book.book_id.desc()).first()
if last_book_id is not None:
setting = db_session.query(Setting).filter(
Setting.bit == 0).one()
setting.book_last_id = last_book_id.book_id
setting.book_last_ran = cutil.get_datetime()
db_session.add(setting)
db_session.commit()
except NoResultFound:
# If there is no raw data then no books were collected
pass
except:
logger.exception("Problem logging last book scraped")
def log_last_scraped(self):
try:
# Find the lowest comic id we did not scrape yet and start there next time
if 404 in self.comic_ids:
# This is never successful because it always returns a 404 page
self.comic_ids.remove(404)
try:
last_comic_id = min(self.comic_ids) - 1
except ValueError:
last_comic_id = self.max_id
setting = db_session.query(Setting).filter(Setting.bit == 0).one()
setting.comic_last_id = last_comic_id
setting.comic_last_ran = cutil.get_datetime()
db_session.add(setting)
db_session.commit()
except:
logger.exception("Problem logging last comic scraped")
def parse(self, response):
"""
:return: Dict the content
"""
rdata = {}
# Parse the items here and return the content to be added to the db
logger.info("Getting comic {comic_id}-{comic_title}".format(
comic_id=response.get('num'), comic_title=response.get('title')))
comic_filename = '{base}/{last_num}/{comic_id}{file_ext}'\
.format(base=self.scraper.BASE_SAVE_DIR,
last_num=str(response.get('num'))[-1],
comic_id=response.get('num'),
file_ext=cutil.get_file_ext(response.get('img'))
)
posted_at = '{year}-{month}-{day}'.format(year=response.get('year'),
month=response.get('month'),
day=response.get('day'))
rdata = {
'comic_id':
response.get('num'),
'alt':
response.get('alt'),
'source_file_location':
response.get('img'),
'saved_file_location':
self.web.download(response.get('img'), comic_filename).replace(
self.scraper.BASE_DATA_DIR + os.path.sep, ''),
'posted_at':
cutil.str_to_date(posted_at, formats=["%Y-%m-%d"]),
'time_collected':
cutil.get_datetime(),
'title':
response.get('title'),
'transcript':
response.get('transcript'),
'raw_json':
json.dumps(response),
}
return rdata
def parse(self, soup):
"""
:return: List of items with their details
"""
# Adds title
rdata = self.web.scraper.archive_list.get(self.comic_id)
# Parse the items here and return the content to be added to the db
img_src = "http://www.questionablecontent.net" + soup.find(
'img', {'id': 'strip'})['src'][1:]
news = soup.find('div', {'id': 'news'}).text.strip()
comic_filename = '{last_num}/{comic_id}.png'\
.format(last_num=str(self.comic_id)[-1],
comic_id=self.comic_id)
rdata.update({
'comic_id': self.comic_id,
'news': news,
'file_path': self.web.download(img_src, comic_filename),
'time_collected': cutil.get_datetime(),
})
return rdata
def parse(self, soup):
"""
:return: List of items with their details
"""
rdata = self.scraper.archive_list.get(self.whatif_id)
# Parse the items here and return the content to be added to the db
article = self.web.driver.find_element_by_css_selector('article.entry')
rdata['question'] = soup.find('article', {'class': 'entry'}).find('p', {'id': 'question'}).get_text()
whatif_filename = '{base}/{last_num}/{whatif_id}.png'\
.format(base=self.scraper.BASE_SAVE_DIR,
last_num=str(self.whatif_id)[-1],
whatif_id=self.whatif_id)
rdata.update({'whatif_id': self.whatif_id,
'saved_file_location': self.web.screenshot(whatif_filename, element=article)
.replace(self.scraper.BASE_DATA_DIR + os.path.sep, ''),
'time_collected': cutil.get_datetime(),
})
return rdata
def parse_book(self, content):
"""
:return: List of items with their details
"""
cover_source = content.find('img',
{'itemprop': 'image'})['src'].strip()
try:
subtitle = content.find('h3').getText().strip()
except AttributeError:
subtitle = None
try:
file_source = content.find(
'a', {'href': re.compile('http://filepi.com')})['href']
except (AttributeError, TypeError):
file_source = None
parsed_data = {
'book_id':
self.book_id,
'file_location':
None,
'file_cover_location':
None,
'file_cover_source':
self.web.scraper.BASE_URL + cover_source,
'description':
content.find('span', {
'itemprop': 'description'
}).getText().strip(),
'file_source':
file_source,
'format':
content.find(attrs={
'itemprop': 'bookFormat'
}).getText().strip().lower(),
'isbn':
content.find(attrs={
'itemprop': 'isbn'
}).getText().strip(),
'language':
content.find(attrs={
'itemprop': 'inLanguage'
}).getText().strip(),
'pages':
content.find(attrs={
'itemprop': 'numberOfPages'
}).getText().strip(),
'publisher':
content.find(attrs={
'itemprop': 'publisher'
}).getText().strip(),
'title':
content.find('h1', {
'itemprop': 'name'
}).getText().strip(),
'subtitle':
subtitle,
'year':
content.find(attrs={
'itemprop': 'datePublished'
}).getText().strip(),
'author':
content.find(attrs={
'itemprop': 'author'
}).getText().strip(),
'time_collected':
cutil.get_datetime(),
}
# Download book
base_filename = '{last_nums}/{book_id}/{book_id}'\
.format(last_nums=self.book_id[-2:], book_id=self.book_id)
book_filename = '{base_filename}_book.{ext}'.format(
base_filename=base_filename, ext=parsed_data.get('format'))
cover_ext = cutil.get_file_ext(parsed_data.get('file_cover_source'))
book_cover_filename = '{base_filename}_cover{ext}'.format(
base_filename=base_filename, ext=cover_ext)
parsed_data['file_cover_location'] = self.web.download(
parsed_data.get('file_cover_source'), book_cover_filename)
header = {'Referer': self.web.scraper.BASE_URL}
if parsed_data.get('file_source') is not None:
parsed_data['file_location'] = self.web.download(
parsed_data.get('file_source'), book_filename, header=header)
return parsed_data
