爬虫的案例成功了

「爱情、让人受尽委屈。」 2022-10-09 00:43 223阅读 0赞

import requests
    from lxml import html
    # url='https://movie.douban.com/' #需要爬数据的网址
    # page=requests.Session().get(url)
    # print(page)
    # tree=html.fromstring(page.text)
    # result=tree.xpath('//td[@class="title"]//a/text()') #获取需要的数据
    
    url = "https://movie.douban.com/"
    
    header = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"
    }
    page = requests.Session().get(url, headers=header)
    # print(page.text)
    print(page)
    tree = html.fromstring(page.text)
    print(tree)
    # print(page.text)
    # /表示绝对路径  //表示相对路径
    result = tree.xpath('//td[@class="title"]//a/text()')
    print(result)
    print('//td[@class="title"]//a/text()')
    print('\n你好')

import requests
    from lxml import html
    
    url = "https://www.baidu.com/more/"
    
    header = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"
    }
    page = requests.Session().get(url, headers=header)
    # print(page.text)
    # print(page)
    page.encoding='utf-8'
    tree = html.fromstring(page.text)
    print(tree)
    # print(page.text)
    # /表示绝对路径  //表示相对路径
    # result = tree.xpath('//td[@class="title"]//a/text()')
    result = tree.xpath('//*[@id="content"]/div/div/a/text()')
    # //*[@id="content"]/div[1]/div[2]/a
    print(result)
    # print('//td[@class="title"]//a/text()')
    # print('\n你好')

大佬：https://blog.csdn.net/csqazwsxedc/article/details/68498842?ops\_request\_misc=&request\_id=&biz\_id=102&utm\_term=%E7%88%AC%E8%99%AB%E4%BB%A3%E7%A0%81&utm\_medium=distribute.pc\_search\_result.none-task-blog-2allsobaiduweb~default-7-.nonecase&spm=1018.2226.3001.4187

爬取网站：https://www.baidu.com/more/

https://www.cnblogs.com/lei0213/p/7506130.html

https://blog.csdn.net/qq\_40558166/article/details/102868801?ops\_request\_misc=%257B%2522request%255Fid%2522%253A%2522162435676916780261949018%2522%252C%2522scm%2522%253A%252220140713.130102334…%2522%257D&request\_id=162435676916780261949018&biz\_id=0&utm\_medium=distribute.pc\_search\_result.none-task-blog-2alltop\_positive~default-2-102868801.first\_rank\_v2\_pc\_rank\_v29&utm\_term=%E7%88%AC%E8%99%AB&spm=1018.2226.3001.4187