Beautifulsoup: Loop durch Klasse und extrahieren Informationen

Question

import requests 
from bs4 import BeautifulSoup 

res = requests.get('https://www.amcham.com.au/web/Events/Web/Events/Upcoming_Events.aspx?hkey=6f098583-ca3d-4a6f-87de-cd4f13d50b11') 
soup = BeautifulSoup(res.text,"lxml") 

event_title = soup.find('span', {'class': 'eventTitle'}) 
event_location = soup.find('span', {'class': 'city'}) 
event_place = soup.find('span', {'class': 'place'}) 
event_date = soup.find('span', {'class': 'eventDate'}) 


print(event_title.text) 
print(event_place.text,event_location.text) 
print(event_date.text) 

Ich verwende diesen Code, um bevorstehende Ereignisse Titel, Ort, Datum Informationen von der Website zu extrahieren.

Ich freue mich darauf, die gesamte Serie auf Veranstaltungen in der Website durchlaufen und Ereignistitel, Ort, Ort, Datum Informationen extrahieren, Kann mir jemand mit dem gleichen helfen?

Answer 1

Sie müssen findAll verwenden, um eine vollständige Liste für jeden zu bekommen:

event_title = [i.text for i in soup.findAll('span', {'class': 'eventTitle'})] 
event_location = [i.text for i in soup.findAll('span', {'class': 'city'})] 
event_place = [i.text for i in soup.findAll('span', {'class': 'place'})] 
event_date = [i.text for i in soup.findAll('span', {'class': 'eventDate'})] 

Answer 2

Ein alternativer Ansatz so etwas wie unten sein kann:

import requests 
from bs4 import BeautifulSoup 

res = requests.get('https://www.amcham.com.au/web/Events/Web/Events/Upcoming_Events.aspx?hkey=6f098583-ca3d-4a6f-87de-cd4f13d50b11') 
soup = BeautifulSoup(res.text,"lxml") 

for item in soup.find_all(class_=["rgRow","rgAltRow"]): 
    event_title = item.find(class_='eventTitle').text 
    event_location = item.find(class_='city').text 
    event_place = item.find(class_='place').text 
    event_date = item.find(class_='eventDate').text 
    print(event_title,event_location,event_place,event_date) 

Answer 3

optimierte Lösung mit Einzel select Abfrage:

import requests, pprint 
import collections 
from bs4 import BeautifulSoup 

res = requests.get('https://www.amcham.com.au/web/Events/Web/Events/Upcoming_Events.aspx?hkey=6f098583-ca3d-4a6f-87de-cd4f13d50b11') 
soup = BeautifulSoup(res.text,"lxml") 

event_data = collections.defaultdict(list) 
for el in soup.select('span.eventTitle, span.city, span.place, span.eventDate'): 
    event_data[el['class'][0]].append(el.text) 

pprint.pprint(dict(event_data)) 

Ziemlich Ausgabe:

{'city': ['The Rocks, NSW', 
      'Brisbane, QLD', 
      'Sydney, NSW', 
      'Richmond, VIC', 
      'Adelaide, SA', 
      'Perth, WA', 
      'Melbourne, VIC', 
      'Pyrmont, NSW', 
      'South Wharf, VIC'], 
'eventDate': ['Mon22Jan', 
       'Mon5Feb', 
       'Fri9Feb', 
       'Tue20Feb', 
       'Fri23Feb', 
       'Thu8Mar', 
       'Wed14Mar', 
       'Thu15Mar', 
       'Mon19Mar', 
       'Tue20Mar', 
       'Wed21Mar', 
       'Fri23Mar', 
       'Wed30May'], 
'eventTitle': ['AMCHAM & UNITED AIRLINES PRESENT', 
       'Super Bowl LII', 
       'AMCHAM SUPER BOWL LII - SYDNEY', 
       'SUPER BOWL LII NETWORKING EVENT', 
       'MR SANJEEV GUPTA', 
       'Meet the Minister Luncheon with The Hon. Alannah MacTiernan', 
       'ADVANCING WOMEN IN LEADERSHIP', 
       'GLOBAL CITIZENS: DRIVING THE FUTURE OF EXPERIENCE', 
       "INTERNATIONAL WOMEN'S DAY", 
       'THE EXECUTIVE SPIN ON SERVICE', 
       'TOLL GROUP', 
       'THE SCIENCE BEHIND LEADERSHIP', 
       'PEAK PERFORMANCE LEADERSHIP SUMMIT', 
       'WORLD BUSINESS FORUM: TWO-DAY EVENT'], 
'place': ['Shangri-La Hotel', 
      'The Pav Bar', 
      'Hotel CBD', 
      'Richmond Football Club', 
      'InterContinental', 
      'CBD Venue', 
      'Karstens', 
      'Sydney CBD', 
      'Plaza Ballroom', 
      'RACV Club', 
      'The Star', 
      'Melbourne Convention Centre']}