|
@@ 2300-2319 (lines=20) @@
|
| 2297 |
|
def get_url_from_archive_element(cls, tr): |
| 2298 |
|
"""Get url corresponding to an archive element.""" |
| 2299 |
|
td_num, td_comic, td_date, _ = tr.find_all('td') |
| 2300 |
|
link = td_comic.find('a') |
| 2301 |
|
return urljoin_wrapper(cls.url, link['href']) |
| 2302 |
|
|
| 2303 |
|
@classmethod |
| 2304 |
|
def get_comic_info(cls, soup, tr): |
| 2305 |
|
"""Get information about a particular comics.""" |
| 2306 |
|
td_num, td_comic, td_date, _ = tr.find_all('td') |
| 2307 |
|
num = int(td_num.string) |
| 2308 |
|
link = td_comic.find('a') |
| 2309 |
|
title = link.string |
| 2310 |
|
imgs = soup.find_all('img', id='comic_image') |
| 2311 |
|
date_str = td_date.string |
| 2312 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p") |
| 2313 |
|
assert len(imgs) == 1 |
| 2314 |
|
assert all(i.get('alt') == i.get('title') for i in imgs) |
| 2315 |
|
return { |
| 2316 |
|
'num': num, |
| 2317 |
|
'title': title, |
| 2318 |
|
'alt': imgs[0].get('alt', ''), |
| 2319 |
|
'img': [i['src'] for i in imgs], |
| 2320 |
|
'month': day.month, |
| 2321 |
|
'year': day.year, |
| 2322 |
|
'day': day.day, |
|
@@ 1968-1986 (lines=19) @@
|
| 1965 |
|
return reversed(get_soup_at_url(archive_url).find_all('td', class_='archive-title')) |
| 1966 |
|
|
| 1967 |
|
@classmethod |
| 1968 |
|
def get_url_from_archive_element(cls, td): |
| 1969 |
|
return td.find('a')['href'] |
| 1970 |
|
|
| 1971 |
|
@classmethod |
| 1972 |
|
def get_comic_info(cls, soup, td): |
| 1973 |
|
"""Get information about a particular comics.""" |
| 1974 |
|
url = cls.get_url_from_archive_element(td) |
| 1975 |
|
title = td.find('a').string |
| 1976 |
|
month_and_day = td.previous_sibling.string |
| 1977 |
|
link_re = re.compile('^%s/([0-9]+)/' % cls.url) |
| 1978 |
|
year = link_re.match(url).groups()[0] |
| 1979 |
|
date_str = month_and_day + ' ' + year |
| 1980 |
|
day = string_to_date(date_str, '%b %d %Y') |
| 1981 |
|
imgs = [soup.find('div', id='comic').find('img')] |
| 1982 |
|
assert len(imgs) == 1 |
| 1983 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 1984 |
|
return { |
| 1985 |
|
'month': day.month, |
| 1986 |
|
'year': day.year, |
| 1987 |
|
'day': day.day, |
| 1988 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 1989 |
|
'title': title, |
SylvainDe /
ComicBookMaker
