crikey.py

from playwright.sync_api import sync_playwright
import re, time # non PEP lol 

class Crikey():
"""Crikey - Create screenshots and test websites using playwright with python
*  any url will work with snip
*  customization still needed for most url_string building
*  would be nice to include some loops of lists


"""
    def __init__(self):
        pass

    def now(self):
        return time.strftime("%Y%m%d-%H%M%S")

    def clean(self,dirt=None):
        if dirt == None:
            print("need string")
            pass
        else:
            cleanish = re.sub(r'^https?://','',dirt)
            clean = re.sub(r'[?.=&/]','_', cleanish)
            return clean

    def snip(self,url=None, screenshot=None):
        if screenshot == None:
            screenshot = f"{self.now()}_{self.clean(url)}.png"

        with sync_playwright() as p:
            browser = p.chromium.launch()
            page = browser.new_page()
            page.goto(url, timeout=6000, wait_until="load")
            time.sleep(3)
            page.screenshot(path=screenshot, full_page=True)
            print(f"{page.title()}\n{url}\n{screenshot}")

    def build_auto_query(self,region="orangecounty", # craigslist fields search strings
                        make="BMW", model="*", 
                        min_yr='2008', max_yr="2018"):
        url = f'https://{region}.craigslist.org/search/\
cta?auto_make_model={make}%20{model}&auto_transmission=1\
&max_auto_year={max_yr}&min_auto_year={min_yr}&query=bmw#search=1~gallery~0~0'
        return url 

if __name__ == "__main__":
    app = Crikey()
    url = app.build_auto_query()
    app.snip(url)