Update open_google_results.py

web_programming/crawl_google_results.py

@@ -1,24 +1,32 @@
-import sys
 import webbrowser
+from sys import argv
+from urllib.parse import quote
 
-import requests
 from bs4 import BeautifulSoup
-from fake_useragent import UserAgent
+from requests import get
 
 if __name__ == "__main__":
+    if len(argv) > 1:
+        query = "%20".join(argv[1:])
+    else:
+        query = quote(str(input("Search: ")))
+
     print("Googling.....")
-    url = "https://www.google.com/search?q=" + " ".join(sys.argv[1:])
-    res = requests.get(url, headers={"UserAgent": UserAgent().random})
-    # res.raise_for_status()
-    with open("project1a.html", "wb") as out_file:  # only for knowing the class
-        for data in res.iter_content(10000):
-            out_file.write(data)
-    soup = BeautifulSoup(res.text, "html.parser")
-    links = list(soup.select(".eZt8xd"))[:5]
 
-    print(len(links))
-    for link in links:
-        if link.text == "Maps":
-            webbrowser.open(link.get("href"))
-        else:
-            webbrowser.open(f"http://google.com{link.get('href')}")
+    url = f"https://www.google.com/search?q={query}&num=2"
+
+    res = get(
+        url,
+        headers={
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:98.0) Gecko/20100101 Firefox/98.0"
+        },
+    )
+
+    link = (
+        BeautifulSoup(res.text, "html.parser")
+        .find("div", attrs={"class": "yuRUbf"})
+        .find("a")
+        .get("href")
+    )
+
+    webbrowser.open(link)