# 案例1
# //為從當(dāng)前html中選取節(jié)點;[@class="c1text1"]為獲取所有的class為c1text1的節(jié)點;/h1[1]為選取的節(jié)點下的第一個h1節(jié)點,如果沒有[1]則是獲取所有的,可以通過循環(huán)進(jìn)行獲取數(shù)據(jù)
etreeHtml.xpath('//*[@class="c1text1"]/h1[1]/text()')

# 案例2
#//為從當(dāng)前html中選取節(jié)點;[@class="c1text1"]為獲取所有的class為c1text1的節(jié)點;/a為獲取當(dāng)前節(jié)點下的所有a標(biāo)簽節(jié)點,得到一個ObjectList;通過for循環(huán)獲取里面每個標(biāo)簽數(shù)據(jù),./@src為獲取當(dāng)前節(jié)點的src屬性值
etreeHtml2 = etreeHtml.xpath('//*[@class="c1text1"]/a')
for _ in etreeHtml2: 
	etreeHtml.xpath(./@src)

# 導(dǎo)入需要的庫
import requests
from lxml import etree
import pymysql


# 文章詳情信息類
class articleData():
    def __init__(self, title, abstract, path,date):
        self.title = title #文章名稱
        self.abstract = abstract #文章摘要
        self.path = path #文章路徑
        self.date = date #發(fā)布時間


    def to_string(self):
        print("文章名稱:"+self.title
              +";文章摘要:"+self.abstract
              +";文章路徑:"+self.path
              +";發(fā)布時間:"+self.date)

#保存狗狗詳情數(shù)據(jù)
#保存數(shù)據(jù)
def saveData(DataObject):
    count = pymysql.connect(
        host='xx.xx.xx.xx',  # 數(shù)據(jù)庫地址
        port=3306,  # 數(shù)據(jù)庫端口
        user='xxxxx',  # 數(shù)據(jù)庫賬號
        password='xxxxxx',  # 數(shù)據(jù)庫密碼
        db='xxxxxxx'  # 數(shù)據(jù)庫名
    )
    # 創(chuàng)建數(shù)據(jù)庫對象
    db = count.cursor()
    # 寫入sql
    # print("寫入數(shù)據(jù):"+DataObject.to_string())
    sql = f"insert into article_detail(title,abstract,alias,path,date) " \
          f"values ('{DataObject.title}','{DataObject.abstract}','{DataObject.path}','{DataObject.date}')"
    # 執(zhí)行sql
    print(sql)
    db.execute(sql)
    # 保存修改內(nèi)容
    count.commit()
    db.close()

# 爬取數(shù)據(jù)的方向
def getWebData():
    # 網(wǎng)站頁面路徑
    url = "https://blog.csdn.net/BadBoyxiaolin?spm=1000.2115.3001.5343"
    # 請求頭，模擬瀏覽器請求
    header = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36"
    }
    # 獲取頁面所有節(jié)點代碼
    html = requests.get(url=url, headers=header)
    # 打印頁面代碼查看
    # print(html.text)
    # 如果亂碼可以設(shè)置編碼格式
    # html.encoding = 'gb2312'
    # 通過xpath獲取數(shù)據(jù)對應(yīng)節(jié)點
    etreeHtml = etree.HTML(html.text)
    dataHtml = etreeHtml.xpath('//*[@class="mainContent"]/div/div/div')
    # 循環(huán)獲取數(shù)據(jù)
    for _ in dataHtml:
        # ''.join()是將內(nèi)容轉(zhuǎn)換為字符串可以后面接replace數(shù)據(jù)進(jìn)行處理
        title = ''.join(_.xpath('./article/a/div[1]/h4/text()'))#文章標(biāo)題
        abstract = ''.join(_.xpath('./article/a/div[2]/text()'))#文章摘要
        path = ''.join(_.xpath('./article/a/@href'))#文章路徑
        date = ''.join(_.xpath('./article/a/div[3]/div/div[2]/text()')).replace(' ','').replace('·','').replace('發(fā)布博客','')#發(fā)布時間
        #初始化文章類數(shù)據(jù)
        article_data = articleData(title,abstract,path,date)
        article_data.to_string() #打印數(shù)據(jù)看看是否對
        #保存數(shù)據(jù)到數(shù)據(jù)庫
        # saveData(article_data)

if __name__ == "__main__":
    getWebData()