added start_page to browser to make getting page quicker

restscrape/browser.py

@@ -11,8 +11,9 @@ class browser:
     def __init__(self,**launch_opts):
         self.browser = None
         self.launch_opts = launch_opts
+        self.page = None
 
-    def restart_browser(self,proxy=None,use_adblock=True):
+    def restart_browser(self,proxy=None,use_adblock=True,start_page='about:blank'):
         if self.browser is not None:
             self.close()
         opts = {}
@@ -25,18 +26,27 @@ class browser:
             opts.setdefault('args',[]).extend(['--disable-extensions-except='+ext, '--load-extension='+ext])
         if proxy is not None:
             opts.setdefault('args',[]).extend(['--proxy-server='+proxy])
+        opts.setdefault('args',[]).append(start_page)
         self.browser = run(pyppeteer.launch(**opts))
+        self.page = run(self.browser.pages())[0]
+        run(self.page.waitForNavigation())
 
     def open(self,url,wait_for = 0):
-        page = run(self.browser.pages())[0]
+        if self.page is None:
+            page = run(self.browser.pages())[0]
         run(page.goto(url))
         time.sleep(wait_for)
-        return run(page.content())
+        return self.get_source()
 
     def close(self):
         run(self.browser.close())
 
+    def get_source(self):
+        if self.page is None:
+            self.page = run(self.browser.pages())[0]
+        return run(self.page.content())
 if __name__ == "__main__":
     b = browser(headless=False)
-    b.restart_browser()
-    page = b.open('https://www.google.com')
+    b.restart_browser(start_page='https://www.google.com')
+    source = b.get_source()
+    b.close()