book/epub-crawler
1
0
Fork 0
mirror of https://github.com/apachecn/epub-crawler.git synced 2025-06-10 11:49:10 +00:00
Code Issues Releases Wiki Activity

2021-11-14 19:28:05

Browse Source
This commit is contained in:
wizardforcel 2021-11-14 19:28:05 +08:00
parent 4e73bd8a5f
commit d353944f2f
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
EpubCrawler/img.py
View File

@ -40,7 +40,7 @@ def tr_download_img(url, imgs, picname):
except Exception as ex: except Exception as ex:
print(ex) print(ex)
def process_img_data_url(url, el_img, imgs): def process_img_data_url(url, el_img, imgs, **kw):
if not re.search(RE_DATA_URL, url): if not re.search(RE_DATA_URL, url):
return False return False
picname = hashlib.md5(url.encode('utf-8')).hexdigest() + '.png' picname = hashlib.md5(url.encode('utf-8')).hexdigest() + '.png'
@ -64,7 +64,7 @@ def process_img(html, imgs, **kw):
el_img = el_imgs.eq(i) el_img = el_imgs.eq(i)
url = get_img_src(el_img) url = get_img_src(el_img)
if not url: continue if not url: continue
if process_img_data_url(url, el_img, imgs): if process_img_data_url(url, el_img, imgs, **kw):
continue continue
if not url.startswith('http'): if not url.startswith('http'):
if kw.get('page_url'): if kw.get('page_url'):