网页抓取:用于分页的XPath

# 示例代码
from lxml import html
import requests

url = 'https://example.com/page'
response = requests.get(url)
tree = html.fromstring(response.content)

# 不准确的XPath
# xpath_expr = '//div[@class="item"]'

# 更准确的XPath
xpath_expr = '//div[@class="item" and contains(text(), "Example")]'
items = tree.xpath(xpath_expr)
print(items)

# 示例代码
from lxml import html
import requests

base_url = 'https://example.com/page/{}'
for page in range(1, 6):
    url = base_url.format(page)
    response = requests.get(url)
    tree = html.fromstring(response.content)
    
    # 通用的XPath表达式
    xpath_expr = '//div[@class="item"]'
    items = tree.xpath(xpath_expr)
    print(f'Page {page} items: {items}')