ask-laftan-anlamaz.md

Ask Laftan Anlamaz

ask_laftan_analamaz.py

import sys
import pandas as pd
from os import path, makedirs
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time


def current_milli_time(): return int(round(time.time() * 1000))


OUTPUT_FILE_DIRECTORY = "C:/ask_laftan_alnamaz/"
CHROME_DRIVER_PATH = "C:/chrome_driver/chromedriver.exe"
PAGE_LOAD_WAIT_TIME = 60
makedirs(OUTPUT_FILE_DIRECTORY, exist_ok=True)
driver = webdriver.Chrome(CHROME_DRIVER_PATH)
driver.implicitly_wait(PAGE_LOAD_WAIT_TIME)

episodelist = [
    "23629",
    "23759",
    "23907",
    "24131",
    "24267",
    "24378",
    "24472",
    "24587",
    "24803",
    "24970",
    "25244",
    "25438",
    "25639",
    "25844",
    "26068",
    "26242",
    "26492",
    "26656",
    "26823",
    "26990",
    "27150",
    "27317",
    "27474",
    "27636",
    "27909",
    "28072",
    "28230",
    "28518",
    "28926",
    "29430",
    "29895"
]

quality = 1080
allEpisodePageLinks = []


try:
    for episodeCodeIndex, singleEpisodeCode in enumerate(episodelist):

        for partIndex in range(1, 9):

            showtvlink = 'http://www.showtv.com.tr/dizi/tum_bolumler/ask-laftan-anlamaz-sezon-1-bolum-1-parca-' + \
                str(partIndex) + '-izle/' + str(singleEpisodeCode)
            parsedname = "Ask_Laftan_Anlamaz_Season_1_Episode_" + \
                str(episodeCodeIndex + 1) + "_Part_" + \
                str(partIndex) + "-" + str(quality) + "p.mp4"

            driver.get(showtvlink)
            elem = driver.find_element_by_class_name("vjs-tech")
            cdnVideoLink = elem.get_attribute("src")
            print(cdnVideoLink)
            underscoreIndex = cdnVideoLink.find("_")
            cdnVideoLink = cdnVideoLink[:underscoreIndex] + \
                str("_1920x1080.mp4")
            print(cdnVideoLink)
            episodeNameElem = driver.find_element_by_class_name("label")
            episodeOfficialName= driver.execute_script("return arguments[0].innerText;", episodeNameElem)
            episodeInfo = {
                "episodeCode": singleEpisodeCode,
                "episodeNumber": (episodeCodeIndex + 1),
                "episodePartNumber": partIndex,
                "episodeName": episodeOfficialName,
                "episodePageLink": showtvlink,
                "episodeVideoLink": cdnVideoLink
            }
            allEpisodePageLinks.append(episodeInfo)
except:
    print("Oops!", sys.exc_info()[0], "occured.")
finally:
    print(allEpisodePageLinks)

    output_path_final = path.join(
        OUTPUT_FILE_DIRECTORY, 'ask_laftan_alnamaz_'+str(current_milli_time())+'_.csv')

    keys = [
        "episodeCode",
        "episodeNumber",
        "episodePartNumber",
        "episodeName",
        "episodePageLink",
        "episodeVideoLink"
    ]

    df = pd.DataFrame(allEpisodePageLinks)
    df.to_csv(output_path_final)

    driver.close()