Started building data extraction tools

4 years ago · d8d00101fa
parent 9850f4c677
commit d8d00101fa
3 changed files with 2884 additions and 1366 deletions
--- a/Parser/NCT00658567.html
+++ b/Parser/NCT00658567.html
--- a/Parser/extraction-lib.py
+++ b/Parser/extraction-lib.py
@ -0,0 +1,8 @@
+from bs4 import BeautifulSoup
+
+if __name__ == "__main__":
+    with open("./NCT00658567.html") as fh:
+        soup = BeautifulSoup(fh, "lxml")
+
+    print(soup)
+
--- a/Parser/parser.py
+++ b/Parser/parser.py