!pip install openpyxl
import requests
from bs4 import BeautifulSoup
from openpyxl import Workbook
def get_search_list(keyword=None,page=1):
url ='http://www.mailiangwang.com/biz/list'
payload ={'keyword':keyword, 'pageid':page}
response = requests.get(url,params=payload)
print(response.url)
print(response.status_code)
get_search_list(u'玉米',1)
name_total = []
caption_total = []
addr_total = []
category_total = []
def get_search_list(keyword=None,page=1):
url ='http://www.mailiangwang.com/biz/list'
payload ={'keyword':keyword, 'pageid':page}
response = requests.get(url,params=payload)
soup = BeautifulSoup(response.text,'lxml')
links = soup.select('body>div.wrap >div.merchantList >div.p_dataList >div.p_dataItem >span.n1 >a')
captions = soup.select('body > div.wrap > divmerchanList > div.p_dataList > div.p_dataIlem > span.n4')
addrs = soup.select('body > div.wrap >div.merchanList >div.p_dataList >div.p_dataItem > span.n5')
categories = soup.select('body > div.wrap >div.merchantList >div.p_dataItem >span.n6')
for link,caption,addr,category in zip(links, captions, addrs, categories):
name_total.append(link.get('title').strip())
caption_total.append(caption.text)
addr_total.append(addr.text)
category_total.append(category.text)
get_search_list('玉米',1)
print(name_total)
print(caption_total)
运行框中没有爬出来的数据
- 写回答
- 好问题 0 提建议
- 追加酬金
- 关注问题
- 邀请回答
-
1条回答 默认 最新
- 无味33 2021-10-18 20:52关注
!pip install openpyxl import requests from bs4 import BeautifulSoup from openpyxl import Workbook def get_search_list(keyword=None,page=1): url ='http://www.mailiangwang.com/biz/list' payload ={'keyword':keyword, 'pageid':page} response = requests.get(url,params=payload) print(response.url) print(response.status_code) get_search_list(u'玉米',1) name_total = [] caption_total = [] addr_total = [] category_total = [] def get_search_list(keyword=None,page=1): url ='http://www.mailiangwang.com/biz/list' payload ={'keyword':keyword, 'pageid':page} response = requests.get(url,params=payload) soup = BeautifulSoup(response.text,'lxml') links = soup.select('body>div.wrap >div.merchantList >div.p_dataList >div.p_dataItem >span.n1 >a') captions = soup.select('body > div.wrap > div.merchantList > div.p_dataList > div.p_dataItem > span.n4') addrs = soup.select('body > div.wrap > div.merchantList >div.p_dataList >div.p_dataItem > span.n5') categories = soup.select('body > div.wrap > div.merchantList >div.p_dataList >div.p_dataItem >span.n6') for link,caption,addr,category in zip(links, captions, addrs, categories): name_total.append(link.get('title').strip()) caption_total.append(caption.text) addr_total.append(addr.text) category_total.append(category.text) get_search_list('玉米',1) print(name_total) print(caption_total)
本回答被题主选为最佳回答 , 对您是否有帮助呢?解决 无用评论 打赏 举报
悬赏问题
- ¥17 pro*C预编译“闪回查询”报错SCN不能识别
- ¥15 微信会员卡接入微信支付商户号收款
- ¥15 如何获取烟草零售终端数据
- ¥15 数学建模招标中位数问题
- ¥15 phython路径名过长报错 不知道什么问题
- ¥15 深度学习中模型转换该怎么实现
- ¥15 HLs设计手写数字识别程序编译通不过
- ¥15 Stata外部命令安装问题求帮助!
- ¥15 从键盘随机输入A-H中的一串字符串,用七段数码管方法进行绘制。提交代码及运行截图。
- ¥15 TYPCE母转母,插入认方向