added extracting weather tutorial

Author: x4nth055

README.md

@@ -38,4 +38,5 @@ This is a repository of all the tutorials of [The Python Code](https://www.thepy
 - ### [Web Scraping](https://www.thepythoncode.com/topic/web-scraping)
     - [How to Access Wikipedia in Python](https://www.thepythoncode.com/article/access-wikipedia-python). ([code](general/wikipedia-extractor))
     - [How to Extract YouTube Data in Python](https://www.thepythoncode.com/article/get-youtube-data-python). ([code](general/youtube-extractor))
+    - [How to Extract Weather Data from Google in Python](https://www.thepythoncode.com/article/extract-weather-data-python). ([code](general/weather-extractor))
 

general/weather-extractor/README.md

@@ -0,0 +1,12 @@
+# [How to Extract Weather Data from Google in Python](https://www.thepythoncode.com/article/extract-weather-data-python)
+To run this:
+- `pip3 install -r requirements.txt`
+- To get the Google weather data of your current region you live in:
+    ```
+    python weather.py
+    ```
+- To get the weather of a specific region in the world:
+    ```
+    python weather.py "New York"
+    ```
+    This will grab the weather information of "New York" state in the US.

general/weather-extractor/requirements.txt

@@ -0,0 +1,2 @@
+requests
+bs4

general/weather-extractor/weather.py

@@ -0,0 +1,77 @@
+
+from bs4 import BeautifulSoup as bs
+import requests
+
+USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36"
+# US english
+LANGUAGE = "en-US,en;q=0.5"
+
+def get_weather_data(url):
+    session = requests.Session()
+    session.headers['User-Agent'] = USER_AGENT
+    session.headers['Accept-Language'] = LANGUAGE
+    session.headers['Content-Language'] = LANGUAGE
+    html = session.get(url)
+    # create a new soup
+    soup = bs(html.text, "html.parser")
+    # store all results on this dictionary
+    result = {}
+    # extract region
+    result['region'] = soup.find("div", attrs={"id": "wob_loc"}).text
+    # extract temperature now
+    result['temp_now'] = soup.find("span", attrs={"id": "wob_tm"}).text
+    # get the day and hour now
+    result['dayhour'] = soup.find("div", attrs={"id": "wob_dts"}).text
+    # get the actual weather
+    result['weather_now'] = soup.find("span", attrs={"id": "wob_dc"}).text
+    # get the precipitation
+    result['precipitation'] = soup.find("span", attrs={"id": "wob_pp"}).text
+    # get the % of humidity
+    result['humidity'] = soup.find("span", attrs={"id": "wob_hm"}).text
+    # extract the wind
+    result['wind'] = soup.find("span", attrs={"id": "wob_ws"}).text
+    # get next few days' weather
+    next_days = []
+    days = soup.find("div", attrs={"id": "wob_dp"})
+    for day in days.findAll("div", attrs={"class": "wob_df"}):
+        # extract the name of the day
+        day_name = day.find("div", attrs={"class": "vk_lgy"}).attrs['aria-label']
+        # get weather status for that day
+        weather = day.find("img").attrs["alt"]
+        temp = day.findAll("span", {"class": "wob_t"})
+        # maximum temparature in Celsius, use temp[1].text if you want fahrenheit
+        max_temp = temp[0].text
+        # minimum temparature in Celsius, use temp[3].text if you want fahrenheit
+        min_temp = temp[2].text
+        next_days.append({"name": day_name, "weather": weather, "max_temp": max_temp, "min_temp": min_temp})
+    # append to result
+    result['next_days'] = next_days
+    return result
+    
+
+if __name__ == "__main__":
+    URL = "https://www.google.com/search?lr=lang_en&ie=UTF-8&q=weather"
+    import argparse
+    parser = argparse.ArgumentParser(description="Quick Script for Extracting Weather data using Google Weather")
+    parser.add_argument("region", nargs="?", help="""Region to get weather for, must be available region.
+                                        Default is your current location determined by your IP Address""", default="")
+    # parse arguments
+    args = parser.parse_args()
+    region = args.region
+    URL += region
+    # get data
+    data = get_weather_data(URL)
+    # print data
+    print("Weather for:", data["region"])
+    print("Now:", data["dayhour"])
+    print(f"Temperature now: {data['temp_now']}°C")
+    print("Description:", data['weather_now'])
+    print("Precipitation:", data["precipitation"])
+    print("Humidity:", data["humidity"])
+    print("Wind:", data["wind"])
+    print("Next days:")
+    for dayweather in data["next_days"]:
+        print("="*40, dayweather["name"], "="*40)
+        print("Description:", dayweather["weather"])
+        print(f"Max temperature: {dayweather['max_temp']}°C")
+        print(f"Min temperature: {dayweather['min_temp']}°C")