Skip to content

Instantly share code, notes, and snippets.

@myvyang
Created October 17, 2018 09:21
Show Gist options
  • Save myvyang/65d7c6c9f1960d35aff8348d43d0bad1 to your computer and use it in GitHub Desktop.
Save myvyang/65d7c6c9f1960d35aff8348d43d0bad1 to your computer and use it in GitHub Desktop.
import requests
import re
url = "https://weibo.com/p/aj/album/loading?ajwvr=6&type=photo&owner_uid=1935400180&viewer_uid=1935400180&since_id=4266739550726685_-1_20180831_-1&page_id=1005051935400180&page=2&ajax_call=1&__rnd=1539765676886"
re_img = "curclear_picSrc=(.*?)%3F"
re_since = "since_id=([0-9_-]+)"
while True:
print(url)
links = []
resp = requests.get(url, headers = {"cookie": cookie})
text = resp.text
imgs = re.findall(re_img, text)
for item in imgs:
links.append(item.replace("%2F", "/"))
f = open("/tmp/links.txt", "a+")
for link in links:
f.write("%s\n" % link)
f.close()
ss = re.findall(re_since, text)
if len(ss) > 0:
since = ss[0]
print(since)
url = "https://weibo.com/p/aj/album/loading?ajwvr=6&type=photo&owner_uid=1935400180&viewer_uid=1935400180&since_id=" + since + "&page_id=1005051935400180&page=2&ajax_call=1&__rnd=1539765676886"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment