#導(dǎo)入需要的模塊
from selenium import webdriver
import time
from lxml import etree
import pymysql
import re

#創(chuàng)建一個(gè)函數(shù)
def my_browers(url, page):

  # 獲取瀏覽器對(duì)象
  browers = webdriver.PhantomJS(executable_path=r'd:\Desktop\pythonjs\phantomjs-2.1.1-windows\bin\phantomjs.exe')
  
  # 用瀏覽器發(fā)起請(qǐng)求
  browers.get(url)
  
  #休息兩秒，頻率低一點(diǎn)，爬的時(shí)間久一點(diǎn)，安全就多一點(diǎn)
  time.sleep(2)
  
   # 獲取頁面信息
  html = browers.page_source
  
  # 調(diào)用頁面解析函數(shù)
  parse_html(html)
  
# 解析頁面信息
def parse_html(html):

  # 生成一個(gè)xpath對(duì)象
  html = etree.HTML(html)

  # 獲取所有的書籍信息列表
  books = html.xpath('//div[contains(@class,"sc-bZQynM")]')

  # 遍歷每一本書籍 然后拿到我們想要的數(shù)據(jù)
  for book in books:
    # 創(chuàng)建一個(gè)存書字典存數(shù)據(jù)用
    book_dict = {}

    # 獲取封面信息
    pic = book.xpath('//img/@src')
    if pic:
      book_dict['pic'] = pic[0]
    else:
      book_dict['pic'] = ''
    # print(pic)

    # 獲取書名
    book_name = book.xpath('//div[@class="title"]/a/text()')
    # print(book_name)
    if book_name:
      book_name = book_name[0]
      # 刪除書名中最后出現(xiàn)的引號(hào)，
      #由于存數(shù)據(jù)庫的時(shí)候書名最后面的引號(hào)會(huì)導(dǎo)致數(shù)據(jù)庫報(bào)錯(cuò)，刪除可以使代碼更健壯
      if '"' in book_name:
        pattern = re.compile(r'"')
        book_name = pattern.sub('', book_name)
      if "'" in book_name:
        pattern = re.compile(r"'")
        book_name = pattern.sub('', book_name)
        # 刪除書名中最后出現(xiàn)的\，存數(shù)據(jù)的時(shí)候書名最后的\會(huì)把sql語句最后的引號(hào)轉(zhuǎn)義，
        #刪除可以使代碼更健壯
      if '\\' in book_name:
        book_name = book_name[:-1]
      book_dict['book_name'] = book_name
    else:
      book_dict['book_name'] = ''

    # 獲取書籍詳情連接
    book_url = book.xpath('//div[@class="title"]/a/@href')
    if book_url:
      book_dict['book_url'] = book_url[0]
    else:
      book_dict['book_url'] = ''

    # 獲取評(píng)分信息
    score_book = book.xpath('//span[@class="rating_nums"]/text()')
    if score_book:
      book_dict['score_book'] = score_book[0]
    else:
      book_dict['score_book'] = ''

    # 獲取出版社信息
    book_detail = book.xpath('//div[@class="meta abstract"]/text()')
    if book_detail:
      # 刪除書詳情中最后出現(xiàn)的引號(hào)；
      book_detail = book_detail[0]
      if "'" in book_detail:
        pattern = re.compile(r"'")
        book_detail = pattern.sub('', book_detail)

      book_dict['book_detail'] = book_detail
    else:
      book_dict['book_detail'] = ''
    print(book_dict)

    # 調(diào)用數(shù)據(jù)庫函數(shù)
    insert_mysql(book_dict)

# 插入數(shù)據(jù)庫
def insert_mysql(book_dict):
  # 連接數(shù)據(jù)庫
  conn = pymysql.connect('localhost', 'root', 'root', 'test', charset='utf8')

  # 創(chuàng)建操作數(shù)據(jù)庫的對(duì)象
  cursor = conn.cursor()

  pic = book_dict['pic']
  book_name = book_dict['book_name']
  book_url = book_dict['book_url']
  score = book_dict['score_book']
  book_detail = book_dict['book_detail']

  sql = f"insert into python_book (pic,book_name,book_url,score,book_detail) " \
     f"VALUE ('{pic}','{book_name}','{book_url}','{score}','{book_detail}')"

  # 執(zhí)行并提交
  cursor.execute(sql)
  conn.commit()


if __name__ == '__main__':
  for i in range(0, 199):
    print('=================下載第{}頁========================'.format(i + 1))
    page = i * 15
    base_url = 'https://book.douban.com/subject_search?search_text=python&cat=1001&start={}'.format(page)
    my_browers(base_url, page)