惠农网_爬取二级网页内容(源码)_一蓑烟雨任平生

最新推荐文章于 2024-07-21 10:29:50 发布

原创最新推荐文章于 2024-07-21 10:29:50 发布 · 1.8k 阅读

15 ·

CC 4.0 BY-SA版权

文章标签：

#python

python 同时被 2 个专栏收录

46 篇文章

订阅专栏

爬虫

35 篇文章

订阅专栏

本文通过爬取惠农网供应大厅的数据，介绍了使用Python进行网页爬取的方法。利用requests库获取网页内容，结合BeautifulSoup进行HTML解析，并通过pymysql将抓取的数据存入数据库。

废话不多说,直接上代码

今天倒霉的网站是惠农网供应大厅

import requests
import pymysql
from bs4 import BeautifulSoup  # 用来解析网页
from fake_useragent import UserAgent
import uuid
import time

cookk = {
    'Cookie': 'sessionId=S_0KHA8RH66NM124OL; Hm_lvt_91cf34f62b9bedb16460ca36cf192f4c=1604907974,1604908122; Hm_lpvt_91cf34f63a8ff527100d30; lmvid.sig=Si_wW_olbim0OMvL1hiezOhV1QMMdZFpUaz_-YYY93w; deviceId=05ac3ef-5c72-405f-be76-83e97e186; hnUserTicket=d67ed8dc-df8a-45fe-85cd-1530efae920d; hnUserId=125807455'}
types = ["sgzw", "sczw", "qcrd", "shuic", "nfjg", "lymm", "zzzm", "mmhc", "nznj", "zyc", "tudi", "package", "fffu"]
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 '
                  'Safari/537.36',
    'Accept-Language': 'zh-CN,zh;q=0.8'
}
pUrl = "https://www.cnhnb.com"
conn = pymysql.connect(host='127.0.0.1', user='root', passwd='123456', db='zhang', charset="utf8mb4")
cur = conn.cursor()
print("连接成功")
for tt in types:
    for i in range(1, 2):  # 爬取第一页到第3页的数据
        headers["User-Agent"] = UserAgent().random
        resp = requests.get(f"https://www.cnhnb.com/p/{tt}-0-0-0-0-{i}", headers=headers, cookies=cookk)
        page_one = BeautifulSoup(resp.content, "html.parser")
        # .find_all('div')[35].
        dd = page_one.find_all("div", class_='product-items')
        print("到这里了")
        if dd is None:
            print("要回去了")
            continue
        pp = 1
        print(dd)
        for ss in dd:  # tr是每一行内容,在所有的行中,遍历每一列的内容
            print(f"{pp}进入分类")
            pp = pp + 1
            v_type = ""
            if tt == "sgzw":
                v_type = "水果"
            elif tt == "sczw":
                v_type = "蔬菜"
            elif tt == "qcrd":
                v_type = "禽畜肉蛋"
            elif tt == "shuic":
                v_type = "水产"
            elif tt == "nfjg":
                v_type = "农副加工"
            elif tt == "lymm":
                v_type = "粮油米面"
            elif tt == "zzzm":
                v_type = "种子种苗"
            elif tt == "mmhc":
                v_type = "苗木花草"
            elif tt == "nznj":
                v_type = "农资农机"
            elif tt == "zyc":
                v_type = "中药材"
            elif tt == "tudi":
                v_type = "土地流转"
            else:
                v_type = "其他"
            # id
            productId = str(uuid.uuid1())
            # 获取链接
            sUrl = pUrl + ss.find('a')['href']
            print(sUrl)
            # 打开网址 获取时间和分类
            resp_two = requests.get(sUrl, headers=headers, cookies=cookk)
            page_two = BeautifulSoup(resp_two.content, "html.parser")
            # 产地
            place = page_two.find('span', class_="fs14 gray6").text.strip()
            v_time = page_two.find("p", class_="update-time").text[5:]
            # 价格
            v_price = ss.find('span').text.strip()
            # 品种名字
            v_name = ss.find('div', class_='title').text.strip()[15:-1].split(" ")[0]
            # 单位
            aa = str(ss.find('div', class_='shops-price').text.strip())
            unit = aa[-3:-1] + aa[-1]
            # 标题
            v_title = ss.find('div', class_='title').text.strip("优选").strip()
            sql = "insert into gong_ying(id,v_name,v_price,v_unit,v_place,v_type,v_title,v_url,v_time) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s)"
            cur.execute(sql, (productId, v_name, v_price, unit, place, v_type, v_title, sUrl, v_time))
            print("sql已执行")
        print("第{}页已结束".format(i))
        conn.commit()
        time.sleep(1)  # 防止服务器蹦了,间隔一秒钟
cur.close()
conn.close()