def parse_html_page(link, publication_year, publication_month, publication_day,
publisher, num_pages, image_url):
soup = goodreads.get_html_page(link)
info_tag = soup.find(itemprop='numberOfPages')
if info_tag != None:
num_pages = info_tag.contents[0].split(' ')[0]
detail = info_tag.parent.next_sibling.next_sibling.contents[0]
p_date = detail.split('Published')[1].split('by')[0].strip()
p_arr = p_date.split(' ')
if len(p_arr) == 3:
publication_year = p_arr[2]
publication_day = p_arr[1][:-2]
publication_month = int(
datetime.strptime(p_arr[0], '%B').strftime('%m'))
elif len(p_arr) == 2:
publication_year = p_arr[1]
publication_month = int(
datetime.strptime(p_arr[0], '%B').strftime('%m'))
elif len(p_arr) == 1:
publication_year = p_arr[0]
publisher = detail.split('by')[1].strip() if len(
detail.split('by')) > 1 else 'Unknown'
image_tag = soup.find(id='coverImage')
if image_tag != None:
image_url = image_tag.get('src')
book_info = dict(publication_year=publication_year,
publication_month=publication_month,
publication_day=publication_day,
publisher=publisher,
num_pages=num_pages,
image_url=image_url)
return book_info
def parse_html_page(link, born_at):
soup = goodreads.get_html_page(link)
birth_date = soup.find(itemprop='birthDate')
if birth_date:
bd = birth_date.string.split(' ').strip()
born_at = datetime.strptime(bd, '%B %d %Y').strftime('%Y/%m/%d')
print ('===========from Goodreads page', born_at)
return born_at