def get_urls(url, selector):
resp = get_html(url, selector)
html = fromstring(resp)
if 'weixin.qq.com' in url:
image_urls = html.xpath('//img/@data-src')
else:
image_urls = html.xpath('//img/@src')
image_urls = [normalize_image_url(url, image_url) for image_url in image_urls]
return image_urls
def get_urls(url, selector):
resp = get_html(url, selector)
html = fromstring(resp)
if 'weixin.qq.com' in url:
image_urls = html.xpath('//img/@data-src')
else:
image_urls = html.xpath('//img/@src')
image_urls = [
normalize_image_url(url, image_url) for image_url in image_urls
]
return image_urls
from upload2cos import upload_image
from watermark import watermark_text, watermark_overlay
# add argument
parser = argparse.ArgumentParser()
parser.add_argument('url', help='target url page')
parser.add_argument('selector', help='target selector')
args = parser.parse_args()
url = args.url
selector = args.selector
# get html, convert it to md
html = get_html(url, selector)
md = html2md(html)
save_md(md)
# find images on the url page
image_urls = get_urls(url, selector)
# upload image to COS, replace with COS access url
for image_url in image_urls:
print(image_url)
image_path = download_image(image_url)
print(image_path)
new_url = upload_image(image_path)
print(new_url)