Merge pull request #21 from htz1992213/main

Fix PubchemRunner
HouGroup · Nov 9, 2023 · ce8411e · ce8411e
2 parents de354fb + 4ab4d4d
commit ce8411e
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 6 deletions.
diff --git a/mdgo/forcefield/pubchem.py b/mdgo/forcefield/pubchem.py
@@ -68,6 +68,7 @@ def __init__(
                 "profile.managed_default_content_settings.images": 2,
             }
             self.options = webdriver.ChromeOptions()
+            self.server = webdriver.ChromeService(chromedriver_dir)
             self.options.add_argument(
                 'user-agent="Mozilla/5.0 '
                 "(Macintosh; Intel Mac OS X 10_14_6) "
@@ -79,7 +80,7 @@ def __init__(
                 self.options.add_argument("--headless")
             self.options.add_experimental_option("prefs", self.preferences)
             self.options.add_experimental_option("excludeSwitches", ["enable-automation"])
-            self.web = webdriver.Chrome(chromedriver_dir, options=self.options)
+            self.web = webdriver.Chrome(options=self.options, service=self.server)
             self.wait = WebDriverWait(self.web, 10)
             self.web.get("https://pubchem.ncbi.nlm.nih.gov/")
             time.sleep(1)
@@ -144,7 +145,8 @@ def _obtain_entry_web(self, search_text: str, name: str, output_format: str) ->
             query = quote(search_text)
             url = "https://pubchem.ncbi.nlm.nih.gov/#query=" + query
             self.web.get(url)
-            time.sleep(1)
+            loaded_element_path = '//*[@id="main-results"]/div[1]/div/ul'
+            self.wait.until(EC.presence_of_element_located((By.XPATH, loaded_element_path)))
             best_xpath = '//*[@id="featured-results"]/div/div[2]' "/div/div[1]/div[2]/div[1]/a/span/span"
             relevant_xpath = (
                 '//*[@id="collection-results-container"]'
@@ -155,10 +157,12 @@ def _obtain_entry_web(self, search_text: str, name: str, output_format: str) ->
                 match = self.web.find_element(By.XPATH, best_xpath)
             else:
                 match = self.web.find_element(By.XPATH, relevant_xpath)
+            self.wait.until(EC.element_to_be_clickable(match))
             match.click()
+            time.sleep(1)
             # density_locator = '//*[@id="Density"]/div[2]/div[1]/p'
-            cid_locator = '//*[@id="main-content"]/div/div/div[1]/' "div[3]/div/table/tbody/tr[1]/td"
-            smiles_locator = '//*[@id="Canonical-SMILES"]/div[2]/div[1]/p'
+            cid_locator = '//*[@id="Title-and-Summary"]/div/div/div/div[1]/div[2]'
+            smiles_locator = '//*[@id="Canonical-SMILES"]/div[2]/div[1]'
             self.wait.until(EC.presence_of_element_located((By.XPATH, cid_locator)))
             cid = self.web.find_element(By.XPATH, cid_locator).text
             smiles = self.web.find_element(By.XPATH, smiles_locator).text

diff --git a/mdgo/util/packmol.py b/mdgo/util/packmol.py
@@ -17,9 +17,8 @@
 import subprocess
 from pathlib import Path
 from typing import Dict, List, Optional, Union
-
-from pymatgen.core import Molecule
 from shutil import which
+from pymatgen.core import Molecule
 
 # from pymatgen.io.core import InputFile, InputSet, InputGenerator