我正在尝试将xml站点地图转换为列表。最终,我不知道如何拨打每一条线路。如果我不能打电话,例如lst[0]
,lst[1]
我无法抓住每个链接,例如title = (get_url()).findAll("div",{"class":"large-7 medium-9 columns"}[0].h1)
教我如何使用
from bs4 import BeautifulSoup
import requests
def get_urls():
baseurl = 'https://link/sitemap.xml'
request = requests.get(baseurl)
response = str(request.content)
soup = BeautifulSoup(response, 'html.parser')
search_html = soup.find_all('url')
results_list = [item.find('loc').decode().split('>', 1)[1].split('<', 1)[0].strip() for item in search_html]
for url in results_list:
retuned_objects(url)
def retuned_objects(url):
print(format(url))
# i = []
# for i in get_urls():
# lnks
lst = [get_urls()]
print(lst[0])
答案 0 :(得分:2)
是的,只需返回results_list
。
from bs4 import BeautifulSoup
import requests
def get_urls():
baseurl = 'https://www.desertessence.com/sitemap.xml'
request = requests.get(baseurl)
response = str(request.content)
soup = BeautifulSoup(response, 'html.parser')
search_html = soup.find_all('url')
results_list = [item.find('loc').decode().split('>', 1)[1].split('<', 1)[0].strip() for item in search_html]
return results_list
lst = get_urls()
print(lst)