initial commit

parse_dl.py

@@ -0,0 +1,18 @@
+from zlib_dl import ZLibSession
+import re
+from bs4 import BeautifulSoup
+s = ZLibSession(verbose=True)
+url = "https://zlib.li/book/mDJxkg7yO6/%E6%B5%AA%E6%BD%AE%E4%B9%8B%E5%B7%85%E7%AC%AC%E5%9B%9B%E7%89%88.html"
+resp = s._request_download(url)
+soup = BeautifulSoup(resp.text, 'html.parser')
+a_tag = soup.find('a', href=re.compile(r"^/dl/\w+"))
+if a_tag:
+    print(f"FOUND: {a_tag['href']}")
+else:
+    print("NOT FOUND")
+    # let's try another heuristic
+    dl_btn = soup.find('a', class_=re.compile(r"addDownloadedBook"))
+    if dl_btn:
+        print("FOUND VIA CLASS:", dl_btn.get("href"))
+    else:
+        print("STILL NOT FOUND")