爬取起点

 

 

查看源代码

 

 

 

 标签

 

 

 

#获取各书的id
import re
import requests
def book_list():
    url = 'https://www.qidian.com/rank'
   # 打开相应url并把页面作为返回
    html = requests.get(url).text
    print(html)
    ren = r' </a><img src="//bookcover.yuewen.com/qdbimg/349573/1010868264/90">'
    ren_url = re.compile(ren)
    book_url = ren_url.findall(html)
    return book_url()

 

 

 

 

 

书名

#获取书名
import re
import requests
def book_name():
    url = 'https://book.qidian.com/info/1010868264'
    html = requests.get(url).text
    ren = r' <h1>.*?<em>(.*?)</em>'
    ren_name = re.compile(ren)
    name = ren_name.findall(html)
    name = ".".join(name)
    print("书名:"+name)
    return name
book_name()

作者

#获取作者
import re
import requests
def book_authorname():
    url = 'https://book.qidian.com/info/1010868264'
    html = requests.get(url).text
    ren = r"authorName: '(.*?)'"
    ren_autorname = re.compile(ren)
    authorname = ren_autorname.findall(html)
    authorname = ".".join(authorname)
    print("作者:" + authorname)
    return authorname
book_authorname()

导入数据库

db = pymysql.connect(host='localhost', port=3306, user='root', password='123', db='spider', charset='utf8')
         cursor = db.cursor()
         sql1 = "insert into bookspider(book_url,book_name,book_authorname) values ('%s','%s','%s')" % (bookurl[0],bookname[0],booksummary[0],bookid[0])
         cursor.execute(sql1)
         db.commit()
         print("存入数据库成功！")