import pymysql
import requests
from lxml import etree


def getDB():
    db = pymysql.connect(host='localhost',user='root',password='123456',database='douban')
    return db

def Agent_info():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36 Edg/123.0.0.0'
    }
    return headers

def get_url():
    headers=Agent_info()
    manh_url = 'https://ac.qq.com/Rank/comicRank/type/top'
    res = requests.get(url=manh_url, headers=headers)
    e = etree.HTML(res.text)
    hrefs = e.xpath('//div/ul/li/a/@href')
    hrefs = hrefs[16:38]
    for i in range(22):
        hrefs[i] = "https://ac.qq.com/" + hrefs[i]
    return hrefs

def get_url_info(manh_url):
    print("抓取网址", manh_url)
    headers = Agent_info()
    res = requests.get(manh_url, headers=headers)
    e = etree.HTML(res.text)
    ranks = e.xpath('//*[@id="special_bg"]/div[3]/div/div/div[2]/div/div[2]/p/strong/text()')
    ranks=str(ranks).strip('[').strip(']')
    names = e.xpath('//*[@id="special_bg"]/div[3]/div/div/div[2]/div/div[1]/h2/strong/text()')
    names=str(names).strip('[').strip(']')
    authors = e.xpath('//*[@id="special_bg"]/div[3]/div/div/div[2]/div/p/span/em/text()')
    authors1 = e.xpath('//*[@id="special_bg"]/div[3]/div/div/div[2]/div/p/span/em/text()')
    authors2 = e.xpath('//*[@id="special_bg"]/div[3]/div/div/div[2]/div/p/span/em/text()')

    authors0 = str(authors).split(',')[0]
    authors0 = authors0[2:-5]
    renqi = str(authors1).split(',')[1]
    shoucang = str(authors2).split(',')[2]
    shoucang=shoucang[:-1]
    print(authors)
    sql = 'insert into manh (names,ranks,renqi,shoucang,urls,authors) values ("{}","{}","{}","{}","{}","{}")'.format(names,ranks,renqi,shoucang,manh_url,authors0)
    db = getDB()
    cursor = db.cursor()
    try:
        cursor.execute(sql)
        db.commit()
    except Exception as e:
        print(e)
        db.rollback()
    cursor.close()
    db.close()
if __name__ == '__main__':

    manh_urls = get_url()
    for url in manh_urls:
        get_url_info(url)