爬取周公解梦数据(一)

最新推荐文章于 2020-07-27 15:56:15 发布

xiaominuo

最新推荐文章于 2020-07-27 15:56:15 发布

阅读量1.6k

点赞数

分类专栏： python 文章标签： mysql python

本文链接：https://blog.csdn.net/qq_40923390/article/details/107611251

版权

python 专栏收录该内容

10 篇文章

订阅专栏

爬取周公解梦主页数据

1.查看周公解梦网站html

在这里插入图片描述

2.代码解析

	url = 'https://www.zgjm.net/b/jiemeng/'
    headers = {
        "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    # json_data = requests.get(url, params=form_data, headers=headers).json()
    json_data = requests.get(url)
    html=json_data.content
    html_doc = str(html,'utf-8')
    soup = BeautifulSoup(html_doc,"lxml")
    urllist = soup.find_all(class_='postitemjm') #获取类为 postitemjm 的标签
    print(urllist)

运行结果：
在这里插入图片描述

3.剩下的就是循环取li标签的href，爬取子页面数据结合数据库保存这些数据

def add_data(type_name,param,key_name):
    url = 'https://www.zgjm.net'+param
    headers = {
        "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    try:
        json_data = requests.get(url)
        html=json_data.content
        # print(html)
        html_doc = str(html,'utf-8')
        soup = BeautifulSoup(html_doc,"lxml")
        content = soup.find(class_='article-content')
        title = soup.find(class_='article-title')

        cur.execute("insert into dream(type,key_name,title,content) VALUES ('"+type_name+"','"+key_name+"','"+str(title.string)+"','"+str(content.text)+"')")
    except UnicodeDecodeError as err:
        print(key_name,"Unicodeerror")
        pass
if __name__ == '__main__':
    conn = pymysql.connect(host=ip,port=port,user='root',passwd='',db='',charset='utf8mb4')
    # print(conn)
    cur = conn.cursor()
    #down_meng()
    add_data('人物','/b/124/','下雪')

    
    cur.close()
    conn.close()

4.最后贴上数据库表结构及所有代码

在这里插入图片描述
数据截图：

最后是所有代码：

import json
import requests
import time
from bs4 import BeautifulSoup
import pymysql
def add_data(type_name,param,key_name):
    url = 'https://www.zgjm.net'+param
    headers = {
        "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    # json_data = requests.get(url, params=form_data, headers=headers).json()
    try:
        json_data = requests.get(url)
        html=json_data.content
        # print(html)
        html_doc = str(html,'utf-8')
        soup = BeautifulSoup(html_doc,"lxml")
        content = soup.find(class_='article-content')
        title = soup.find(class_='article-title')

        cur.execute("insert into dream(type,key_name,title,content) VALUES ('"+type_name+"','"+key_name+"','"+str(title.string)+"','"+str(content.text)+"')")
    except UnicodeDecodeError as err:
        print(key_name,"Unicodeerror")
        pass
    
def down_meng():
    url = 'https://www.zgjm.net/b/jiemeng/'
    headers = {
        "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    # json_data = requests.get(url, params=form_data, headers=headers).json()
    json_data = requests.get(url)
    html=json_data.content
    html_doc = str(html,'utf-8')
    soup = BeautifulSoup(html_doc,"lxml")
    urllist = soup.find_all(class_='postitemjm')
    # print(urllist)
    arr = {0:"人物",1:"动物",2:"植物",3:"物品",4:"活动",5:"情感",6:"生活",7:"鬼神",8:"自然",9:"建筑",10:"其他"}
    i = 0
    for url_list in urllist:
        li_list = url_list.find_all('li')
        for lilist in li_list:
            print(lilist.a.string,"完成")
            add_data(arr[i],lilist.a['href'],lilist.a.string)
        i = i+1
        conn.commit()
        time.sleep(3)

if __name__ == '__main__':
    conn = pymysql.connect(host=ip,port=port,user='root',passwd='',db=db,charset='utf8mb4')
    # print(conn)
    cur = conn.cursor()
    down_meng()
    # add_data('人物','/b/124/','下雪')
    cur.close()
    conn.close()