第一次照着视频写python

采集电影天堂下载链接

视频地址：邀请你看《Python爬虫教程：零基础学爬虫》https://url.cn/5H9sxCv?sf=uri

使用版本3.72

使用时报错没有库解决办法

打开cmd 进入安装目录禅道Scripts文件夹

cd C:\Python\Python37\Scripts

使用pip install  requests

使用pip install  re

使用pip install  pymysql

 

数据库名字dytt8

数据库用户名密码  root   root

字符  utf8

SET FOREIGN_KEY_CHECKS=0;

DROP TABLE IF EXISTS `dytt8`;
CREATE TABLE `dytt8` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `title` varchar(255) DEFAULT NULL,
  `content` text,
  `link` text,
  PRIMARY KEY (`id`)
) ENGINE=MyISAM AUTO_INCREMENT=428 DEFAULT CHARSET=utf8;

 

全部代码

import  requests
import re
import pymysql

db = pymysql.connect(host='localhost',port=3306,user='root',passwd='root',db='py',charset='utf8')
cursor = db.cursor()
def getMovieList(page):
  print ('第',page,"页")
  res =  requests.get('https://www.dytt8.net/html/gndy/dyzz/list_23_{}.html'.format(page))
  res.encoding = 'gb2312'
  result = res.text
  reg = r'<a href="(.*?)" class="ulink">(.*?)</a>'
  reg = re.compile(reg)
  return re.findall(reg,result)

def getMoveContent(url,title):
  res = requests.get('https://www.dytt8.net{}'.format(url))
  res.encoding = 'gb2312'
  result = res.text
  reg = r'<div class="co_content8">(.*?)<strong><font color="#ff0000">.*?<a href="(.*?)"'
  reg = re.compile(reg,re.S)
  #如果错误则忽略返回空值
  try:
    content, link = re.findall(reg, result)[0]
    print (link,'已保存')
  except:
    print ('错误忽略')
    return

  sql = "insert into dytt8(title,content,link) values('{}','{}','{}')".format(title,content.replace("'","\\'"),link)
  cursor.execute(sql)

for page in range(1,16):
  for url,title in getMovieList(page):
    getMoveContent(url,title)
    # break