import requests
from bs4 import BeautifulSoup
from lxml import etree
from multiprocessing import Pool
import pymysql

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 ' \
                               '(KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
}

conn = pymysql.connect(host='localhost',user='root',passwd='123456',db='mydb',port=3306,charset='utf8')
cursor = conn.cursor()

def get_jianshu_info(url):
    res = requests.get(url,headers=headers)
    selector = etree.HTML(res.text)
    infos = selector.xpath('//ul[@class="note-list"]/li')
    for info in infos:
        try:
            title = info.xpath('div/a/text()')[0]
            author =info.xpath('div / div / a[1]/text()')[0]
            content = info.xpath('div/p/text()')[0].strip()
            comment = info.xpath('div/div/a/text()')[2].strip()
            if len(comment)==0:
                comment = '无'
            like = info.xpath('div/div/span[1]/text()')[0].strip()
            if len(like) == 0 and 11:
                like = '无'
            reward = info.xpath('div/div/span[2]/text()')
            if len(reward) == 0:
                reward = '无'
            else:
                reward = reward[0].strip()
            cursor.execute(
                "insert into jianshureping (like,reward) "
                "values (%s,%s)",
                (str(like),str(reward))
            )
            conn.commit()
            print('ok')
        except IndexError:
            print('error')



if __name__ == '__main__':
    urls = \
        ['https://www.jianshu.com/c/bDHhpK?order_by=commented_at&page={}'.format(str(i)) for i in range(1, 3)]
    for url in urls:
        get_jianshu_info(url)