國家機器

# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from time import sleep
import pandas as pd
options = webdriver.ChromeOptions()


options.add_argument('disable-infobars')
acc = input("輸入查詢帳號 :")
# add here any tag you want.
browser = webdriver.Chrome(chrome_options=options)
value = 1
browser.get("https://forum.gamer.com.tw/B.php?bsn=60076&subbsn=0")

browser.find_element_by_class_name("material-icons").click()
sleep(0.3)
a = browser.find_elements_by_class_name("gcse-sort-title")[1]
a.click()
sleep(0.3)
browser.find_element_by_id("old_search_input").send_keys(acc)
browser.find_element_by_id("old_search_input").send_keys(Keys.ENTER)
sleep(0.3)

while True:
    i = 0
    print(value)
    browser.get("https://forum.gamer.com.tw/Bo.php?page="+str(value)+"&bsn=60076&q="+acc+"&tnum=1342")
    sleep(0.3)
    b = browser.find_elements_by_xpath("//a[@data-gtm='Bo頁文章列表']")
    sleep(0.3)
    c = len(b)
    value +=1
    while (c) > i :
        print(i+1)
        sleep(0.5)
        testTime = browser.find_elements_by_class_name("FM-blist6")
        testa = browser.find_elements_by_xpath("//a[@data-gtm='Bo頁文章列表']")
        wordone = testa[i].text
        wordtwo = testTime[i].text
        sleep(0.3)
        testa[i].click()
        try:
            show = browser.find_element_by_css_selector(".show")
            print("find show")
            show.click()
            sleep(1)
        except:
            print("what")
        texta = browser.find_element_by_class_name("c-article__content")
        try:
            findimg = browser.find_element_by_class_name("photoswipe-image")
            print("find Img")
            print(findimg.get_attribute("href"))
            select = pd.DataFrame({'主題': [wordone],
                '日期': [wordtwo],
                '內容': [texta.text],
                "圖片":[findimg.get_attribute("href")]})
            sleep(1)
        except:
            print("No img")
            select = pd.DataFrame({'主題': [wordone],
                '日期': [wordtwo],
                '內容': [texta.text],
                "圖片":[""]})

        select.to_csv("text.csv",mode='a', header=False,index=False)
        sleep(0.5)
        browser.back()
        i +=1
    sleep(0.3)

#j2492104