Question

<html>
<head>
  <title>Guess the Number</title>
</head>
<body>
  <div id="header">
    <h1 id="title">Guess the Number</h1>
  </div>
  <div id="menu">
    <u><h2>Level Select</h2></u>
    <br>
    <button id="easy" onclick="easy()"><b>Easy</b></button>
    <button id="medium" onclick="medium()"><b>Medium</b></button>
    <button id="hard" onclick="hard()"><b>Hard</b></button>
    <button id="insane" onclick="insane()"><b>Insane</b></button>
  </div>
</body>
</html>

您好，我仍然是使用Python语言的初学者，我想知道如何应用该脚本能够将数据获取网站下一页数据的功能？

我尝试做

from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup

my_url = 'https://www.eventbrite.com/d/malaysia--kuala-lumpur--85675181/all- 
events/?page=1'

#opening connection , downloading page
uClient = uReq(my_url)
page_html = uClient.read()
uClient.close()

# html parser
page_soup = soup(page_html, "html.parser")

# catch each events
card = page_soup.findAll("div",{"class":"eds-media-card-content__content"})

filename = "Data_Events.csv"
f = open(filename, "w")

headers = "events_name, events_dates, events_location, events_fees\n"

f.write(headers)

for activity in card :

    event_activity = activity.findAll("div",{"class":"eds-event- 
card__formatted-name--is-clamped"})
    events_name = event_activity[0].text

    event_date = activity.findAll("div",{"class":"eds-text-bs--fixed eds- 
    text-color--grey-600 eds-l-mar-top-1"})
    events_dates = event_date[0].text
    events_location = event_date[1].text
    events_fees = event_date[2].text

    print("events_name: " + events_name)
    print("events_dates: " + events_dates)
    print("events_location: " + events_location)
    print("events_fees: " + events_fees)

    f.write(events_name + "," + events_dates + "," + events_location + "," + 
events_fees + "\n")

f.close()

任何建议将不胜感激

Answer 1

import itertools
import requests
from bs4 import BeautifulSoup

def parse_page(url, page)
    params = dict(page=page)
    resp = requests.get(url, params=params) # will format `?page=#` to url
    soup = BeautifulSoup(resp.text, 'html.parser')
    ... # parse data from page


url = 'https://www.eventbrite.com/d/malaysia--kuala-lumpur--85675181/all-events'

for page in itertools.count(start=1): # don't need to know total pages
    try:
        parse_page(url, page)
    except Exception:
        # `parse_url` was designed for a different page layout and will
        # fail when no more pages to scrape, so we break here
        break

如何使用BeautifulSoup4将数据抓取到Python的最后一页？

1 个答案: