import sys
import requests
from bs4 import BeautifulSoup

# 推送百度爬蟲
def push_page(url):
    headers = {
        'User-Agent': 'curl/7.12.1',
        'Host': 'data.zz.baidu.com',
        'Content-Type': 'text/plain',
        'Content-Length': '83'
    }
    urls = "http://data.zz.baidu.com/urls?site=https://www.lyshark.com&token=xxxxxxx"
    try:
        html = requests.post(urls, headers=headers, data=url, timeout=5).text
        push_status = eval(html)['success']
        if push_status == 1:
            return 1
        else:
            return 0
    except:
        return 0

# 獲取路徑
def get_page(page):
    html = requests.get(page,timeout=5).text
    try:
        bs = BeautifulSoup(html,"html.parser")
        ret = bs.select('div[class="container"] div[class="row"] h2[class="post-title"] a')
        for item in ret:
            push_url = item.get('href')
            push_ref = push_page(push_url)
            print("推送: {} --> 狀態(tài): {}".format(push_url,push_ref))
        return 1
    except:
        return 0

if __name__ == "__main__":
    arg = sys.argv
    get_page(arg[1])