『退屈なことはPythonにやらせよう』その9(11章:Webスクレイピング)

#celenium xpath example
title_elems = browser.find_element_by_xpath('//input[@data-test-id="compose-subject"]')

#! python3
# check11_1.py  -  コマンドライン電子メーラー
# Usage
# python check11_1.py <sending mail address> <title> <text>

from selenium import webdriver
import sys
import time


print("Usage: python check11_1.py <sending mail address> <title of email> <text>")

#ドライバーの準備
browser = webdriver.Firefox(executable_path = r"C:\\Users\\~~\\geckodriver.exe") #geckodriver.exeまでのパス

USER_ID = "メールのユーザー名"
PASSWORD = "メールのパスワード"

#yahooへのログイン
browser.get("https://login.yahoo.com/?.src=ym")
email_elem = browser.find_element_by_id("login-username")
email_elem.send_keys(USER_ID)
email_elem.submit()
time.sleep(5)

password_elem = browser.find_element_by_id("login-passwd")
password_elem.send_keys(PASSWORD)
password_button = browser.find_element_by_id("login-signin")
password_button.click()
time.sleep(10)

#メール画面に移動
compose_elem = browser.find_element_by_xpath('//a[@data-test-id="compose-button"]')
compose_elem.click()
time.sleep(15)

#アドレス入力
address_elem = browser.find_element_by_id("message-to-field")
address_elem.send_keys(str(sys.argv[1]))
time.sleep(5)

#タイトル入力
title_elems = browser.find_element_by_xpath('//input[@data-test-id="compose-subject"]')
title_elems.send_keys(str(sys.argv[2]))
time.sleep(5)

#本文入力
text_elems = browser.find_element_by_xpath('//div[@data-test-id="rte"]')
text_elems.send_keys(" ".join(sys.argv[3:]))
time.sleep(15)

#送信
send_elems = browser.find_element_by_xpath('//button[@data-test-id="compose-send-button"]')
send_elems.click()

#! python3
# check11_2.py  -  XKCDコミックをひとつずつダウンロードするのと近いやつ

import requests, os, bs4, sys, re

url = "https://www.flickr.com/"
os.makedirs("flickr", exist_ok=True)

#キーワードを文字列に
key_words = "+".join(sys.argv[1:])


#flickrにRequestを送る
res = requests.get("https://www.flickr.com/search/?text=" + key_words)
res.raise_for_status()

#soupの用意
soup = bs4.BeautifulSoup(res.text, features="html.parser")
links = soup.select(".photo-list-photo-view")

#example of url
#url(//live.staticflickr.com/6188/6113679188_6fd95914cf_m.jpg)

for i in range(len(links)):
    img_url = re.search(r"url\((.+?)\)", links[i].get("style")).group(1)
    print("https:" + img_url)

    #ダウンロード
    img = requests.get("https:" + img_url)
    img.raise_for_status()
    img_file = open(os.path.join("flickr", os.path.basename(img_url)), "wb")
    for chunk in img.iter_content(100000):
        img_file.write(chunk)
    img_file.close()

print("Done")

#! python3
# check11_3.py  -  2048を攻略するコード
# url of 2048 is "https://gabrielecirulli.github.io/2048"

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import sys
import time

#ドライバーの準備
browser = webdriver.Firefox(executable_path = r"C:\\Users\\~~\\geckodriver.exe") #geckodriver.exeまでのパス

GAME_URL = "https://gabrielecirulli.github.io/2048"
NEW_GAME_BUTTON = "restart-button" 
RETRY_BUTTON = "retry-button"

#2048 games
browser.get(GAME_URL)
time.sleep(10)

#elems
game_elem = browser.find_element_by_tag_name("html")
try:
    while True:
        game_elem.send_keys(Keys.UP)
        time.sleep(0.05)
        game_elem.send_keys(Keys.RIGHT)
        time.sleep(0.05)
        game_elem.send_keys(Keys.DOWN)
        time.sleep(0.05)
        game_elem.send_keys(Keys.LEFT)
        time.sleep(0.05)
except KeyboardInterrupt:
    print("Done")