def main():
try:
#gob
URL = "https://es.marvelcdb.com/set/" + "trors"
html = zipper.get_html(URL)
scrapeMain(html, "TheRiseOfRedSkull")
except Exception as e:
print(e)
def obtainIssueImages(co_url : str):
co_html : BeautifulSoup = zipper.get_html(co_url)
# text treating
images_to_do = obtainIssueImagesByText(co_html)
#if 0 >= len(images_to_do):
# html treating
#obtainIssueImagesByHtml(co_html)
return images_to_do
def scrapeIssue(url: str, dir: str):
imgs = zipper.get_html(url).findAll(
'img', src=True, attrs={'class': 'img-responsive img-vertical-card'})
imgs_count = 0
for img in imgs:
title = "card-{}.jpg".format(card_idx)
img_url = img['src']
if not (img_url.startswith('http')):
img_url = "https://es.marvelcdb.com" + img_url
print(" " + title + ": " + img_url, )
zipper.get_image(img_url, dir + "/" + title)
imgs_count += 1
inc_card_idx()
print(url + " - Imagenes procesadas = {}".format(imgs_count))
def main():
try:
# comic to scrape
title : str = 'Conan-the-Barbarian-1970'
# dir destiny
dir = title.replace(':', '_').replace(',', '_').replace(' ', '_').replace('(', '').replace(')', '')
if not os.path.exists(dir):
os.makedirs(dir)
# scrape all comic items
html = zipper.get_html(URL + "/Comic/" + title)
scrapeComic(html, dir)
# zip result directory with cbz extension
zipper.zip(dir, dir + '.cbz')
except Exception as e:
print(e)
def main():
try:
URL = 'https://readcomiconline.to/Comic/'
title = 'The-Savage-Sword-Of-Conan'
html = zipper.get_html(URL + title)
# dir destiny
dir = title.replace(':', '_').replace(',',
'_').replace(' ', '_').replace(
'(', '').replace(')', '')
if not os.path.exists(dir):
os.makedirs(dir)
issue_idx = 96
scrapeMain(html, dir, issue_idx)
zipper.zip(dir, dir + '.cbz')
#scrapeIssue('TPB', 'https://readcomiconline.to/Comic/Marvel-Zombies-2006/TPB?id=158840', 'Marvel_Zombies_(2006)/issue-TPB')
except Exception as e:
print(e)
def scrapeIssue(co_title: str, co_url: str, co_dir: str):
print(" " + co_title + ": " + co_url)
if not os.path.exists(co_dir):
os.makedirs(co_dir)
co_html = zipper.get_html(co_url).prettify()
img_idx = 0
html_idx: int = co_html.find('lstImages.push')
while -1 != html_idx:
co_html = co_html[html_idx:]
img_url = co_html[:co_html.find('");')]
img_url = img_url.replace('lstImages.push("', '').replace('")', '')
img_title = "img-" + str(img_idx).zfill(3) + ".jpg"
print(img_title + ": " + img_url)
zipper.get_image(img_url, co_dir + "/" + img_title)
# next img
img_idx = img_idx + 1
co_html = co_html[co_html.find(';'):]
html_idx = co_html.find('lstImages.push')
time.sleep(5)