Python 抓取循环

Question

所以，我需要帮助，这是 mi 代码

results=[]
import re

for i in popup_linkz:  # Here I take N links like this one https://www.mercadopublico.cl/Procurement/Modules/RFB/DetailsAcquisition.aspx?qs=uEap3sWEgifS2G+m9xvYiA==  to iterate thorught them a scraping

   url=i # so right now I scrape the iterating urls
  
    response = requests.get(url)
    print('url:', response.url)     
 #print('status:', response.status_code)
                
soup = BeautifulSoup(response.content, "html.parser")
results=[]
#json_res = json.loads(res.text)
#print(json_res[0]['price']) 
item_1='grvProducto_ctl02_lblCategoria'

for line in soup.findAll('span', attrs={'id': 'grvProducto_ctl02_lblCategoria'}):
    

   results.append(line.text) 
#this actually get the first code, but don't know how to iterate for others, also doesn't store every code on it, when I print doesn't stack them , show them single on print.
  
   print('id',results)

我正在尝试从这个 urlsample >https://www.mercadopublico.cl/Procurement/Modules/RFB/DetailsAcquisition.aspx?qs=uEap3sWEgifS2G+m9xvYiA== 实际上它迭代了 2 到 10.000 个。

information I want to get here but that cant get it

我不确定如何使用它

 for line in soup.findAll('span', attrs={'id': 'grvProducto_ctl02_lblCategoria'}):
        
    
       results.append(line.text)

使用相同的循环获取其他信息。 data of page underlying

你能给我讲讲吗？

Answer 1

尝试：

import requests
from bs4 import BeautifulSoup


url = "https://www.mercadopublico.cl/Procurement/Modules/RFB/DetailsAcquisition.aspx?qs=uEap3sWEgifS2G+m9xvYiA=="
soup = BeautifulSoup(requests.get(url).content, "html.parser")


licitation_number = soup.select_one("#lblNumLicitacion").text
responsable = soup.select_one("#lblResponsable").text
ficha = soup.select_one("#lblFicha2Reclamo").text

print(f"{licitation_number=}")
print(f"{responsable=}")
print(f"{ficha=}")
print("-" * 80)

for t in soup.select("#grvProducto .borde_tabla00"):
    categoria = t.select_one('[id$="lblCategoria"]').text
    candidad = t.select_one('[id$="lblCantidad"]').text
    descripction = t.select_one('[id$="lblDescripcion"]').text
    print(f"{categoria=} {candidad=}")
    print(f"{descripction=}")
    print()

打印：

licitation_number='1549-5-LR22'
responsable='SERVICIO DE SALUD METROPOLITANA NORTE HOSPITAL SAN JOSE, Hospital San  José'
ficha='107'
--------------------------------------------------------------------------------
categoria='42221501' candidad='130'
descripction='(226-2001) STENT CORONARIO DE CROMO COBALTO, LIBERADOR DE FÁRMACO EVEROLIMUS'

categoria='42221501' candidad='360'
descripction='(226-2002) STENT CORONARIO DE CROMO COBALTO, LIBERADOR DE FÁRMACO ZOTAROLIMUS'

categoria='42221501' candidad='120'
descripction='(226-2004) STENT CORONARIO DE CROMO COBALTO, LIBERADOR DE FÁRMACO SIROLIMUS, CON STRUT DE 0.80'

categoria='42221501' candidad='240'
descripction='(226-2003) STENT CORONARIO DE CROMO COBALTO, LIBERADOR DE FÁRMACO SIROLIMUS, CON STRUT DE 0.60'

Python 抓取循环

Python scraping loop

python

loops

web-scraping

scrape

spyder