爬虫-豆瓣活动页面（利用beautifulsoup定位资源）

from bs4 import BeautifulSoup
import requests

url = 'https://beijing.douban.com/events/week-party'
response = requests.get(url)


# with open('douban_party.html', 'wb') as f:
#     f.write(response.content)

soup = BeautifulSoup(response.text, 'lxml')

# li_tag_list = soup.find_all('li', class_="list-entry")
li_tag_list = soup.select('ul.events-list.events-list-pic100.events-list-psmall > li.list-entry')

for li_tag in li_tag_list:
    #summary = li_tag.find('span', itemprop="summary").text
    summary = li_tag.select('span[itemprop="summary"]')[0].text
    #event_time = li_tag.find('li', class_="event-time").text.strip()
    event_time = li_tag.select('li.event-time')[0].text
    fee = li_tag.find('li', class_="fee").text
    host_info = li_tag.select('ul.event-meta > li:nth-of-type(4)')[0].text

    print(summary)
    print(event_time)
    print(fee)
    print(host_info)
    print('-----------------------------------------------------')from bs4 import BeautifulSoup
import requests

url = 'https://beijing.douban.com/events/week-party'
response = requests.get(url)


# with open('douban_party.html', 'wb') as f:
#     f.write(response.content)

soup = BeautifulSoup(response.text, 'lxml')

# li_tag_list = soup.find_all('li', class_="list-entry")
li_tag_list = soup.select('ul.events-list.events-list-pic100.events-list-psmall > li.list-entry')

for li_tag in li_tag_list:
    #summary = li_tag.find('span', itemprop="summary").text
    summary = li_tag.select('span[itemprop="summary"]')[0].text
    #event_time = li_tag.find('li', class_="event-time").text.strip()
    event_time = li_tag.select('li.event-time')[0].text
    fee = li_tag.find('li', class_="fee").text
    host_info = li_tag.select('ul.event-meta > li:nth-of-type(4)')[0].text

    print(summary)
    print(event_time)
    print(fee)
    print(host_info)
    print('-----------------------------------------------------')

转载于:https://www.cnblogs.com/luwanhe/p/9526485.html