import requests
from bs4 import BeautifulSoup
def trade_spider(max_pages):
page = 1
while page <= max_pages:
url = 'https://thenewboston.com/search.php?type=1&sort=pop&page=' + str(page) #https://thenewboston.com/search.php?page=
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a',{'class': 'user-name'}):
href = link.get('href')
title = link.string
#print(href)
#print(title)
get_single_item_data(href)
page +=1
def get_single_item_data(item_url):
source_code = requests.get(item_url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for item_name in soup.findAll('div', {'class': 'profile - full - name'}):
print(item_name.string)
trade_spider(1)
Python 27 Programming Tutorial Web Crawling
最后编辑于 :
©著作权归作者所有,转载或内容合作请联系作者
- 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
- 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...