|
@@ 2223-2242 (lines=20) @@
|
| 2220 |
|
archive_url = urljoin_wrapper(cls.url, 'archive/') |
| 2221 |
|
# The first 2 <tr>'s do not correspond to comics |
| 2222 |
|
return get_soup_at_url(archive_url).find('table', id='chapter_table').find_all('tr')[2:] |
| 2223 |
|
|
| 2224 |
|
@classmethod |
| 2225 |
|
def get_url_from_archive_element(cls, tr): |
| 2226 |
|
"""Get url corresponding to an archive element.""" |
| 2227 |
|
td_num, td_comic, td_date, _ = tr.find_all('td') |
| 2228 |
|
link = td_comic.find('a') |
| 2229 |
|
return urljoin_wrapper(cls.url, link['href']) |
| 2230 |
|
|
| 2231 |
|
@classmethod |
| 2232 |
|
def get_comic_info(cls, soup, tr): |
| 2233 |
|
"""Get information about a particular comics.""" |
| 2234 |
|
td_num, td_comic, td_date, _ = tr.find_all('td') |
| 2235 |
|
num = int(td_num.string) |
| 2236 |
|
link = td_comic.find('a') |
| 2237 |
|
title = link.string |
| 2238 |
|
imgs = soup.find_all('img', id='comic_image') |
| 2239 |
|
date_str = td_date.string |
| 2240 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p") |
| 2241 |
|
assert len(imgs) == 1 |
| 2242 |
|
assert all(i.get('alt') == i.get('title') for i in imgs) |
| 2243 |
|
return { |
| 2244 |
|
'num': num, |
| 2245 |
|
'title': title, |
|
@@ 1914-1932 (lines=19) @@
|
| 1911 |
|
url = 'http://invisiblebread.com' |
| 1912 |
|
|
| 1913 |
|
@classmethod |
| 1914 |
|
def get_archive_elements(cls): |
| 1915 |
|
archive_url = urljoin_wrapper(cls.url, 'archives/') |
| 1916 |
|
return reversed(get_soup_at_url(archive_url).find_all('td', class_='archive-title')) |
| 1917 |
|
|
| 1918 |
|
@classmethod |
| 1919 |
|
def get_url_from_archive_element(cls, td): |
| 1920 |
|
return td.find('a')['href'] |
| 1921 |
|
|
| 1922 |
|
@classmethod |
| 1923 |
|
def get_comic_info(cls, soup, td): |
| 1924 |
|
"""Get information about a particular comics.""" |
| 1925 |
|
url = cls.get_url_from_archive_element(td) |
| 1926 |
|
title = td.find('a').string |
| 1927 |
|
month_and_day = td.previous_sibling.string |
| 1928 |
|
link_re = re.compile('^%s/([0-9]+)/' % cls.url) |
| 1929 |
|
year = link_re.match(url).groups()[0] |
| 1930 |
|
date_str = month_and_day + ' ' + year |
| 1931 |
|
day = string_to_date(date_str, '%b %d %Y') |
| 1932 |
|
imgs = [soup.find('div', id='comic').find('img')] |
| 1933 |
|
assert len(imgs) == 1 |
| 1934 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 1935 |
|
return { |
SylvainDe /
ComicBookMaker
