根据委托单位名称查询样品信息（新三和）

import requests
from bs4 import BeautifulSoup
import pandas as pd

将委托单位名称转化成utf-8格式，并用%连接转化后16进制，导入cabr-betc报告的查询网址url中

text = “山东鲁泰装配式装修材料有限公司”
print(f"新三和系统根据委托单位名称进行查询：{text}“)
utf8_encoded_text = text.encode(‘utf-8’)
hex_representation = ‘%’.join(hex(b)[2:] for b in utf8_encoded_text)
#print(hex_representation)
url = “http://weixin.cabr-betc.com/gzsjcwx/WxMainGj/findreport?prtnum=&wtnum=&phnum=&gccode=&gcname=&wtunit=%”+hex_representation+”&wtdatee=&wtdater=&contractcode=&customerId=&xmName="
print(f"查询网址：{url}")
print(‘’)

发送 GET 请求获取网页内容

response = requests.get(url)
#print(response.text)

使用 BeautifulSoup 解析网页内容

soup = BeautifulSoup(response.text, ‘html.parser’)
#print(soup)

查找所有报告编号元素并打印

data_list = []
data = []
count = 0

boxes = soup.find_all(‘div’, class_=‘PrtInfoDiv-detail-box’)
#print(div_tags)
for box in boxes:
spans = box.find_all(‘span’)
for span in spans:
#print(span.get_text().strip())
data.append(span.get_text().strip())

        count += 1
        if count == 12:
            data_list.append(data)
            print(data[5::2])
            data = []
            count = 0