Python BeautifulSoup和请求解析问题

尝试使用BeautifulSoup和请求模块时出错

我的代码如下：

import requests
from bs4 import BeautifulSoup

def get_html(url):
    url = ('https://m.vk.com/bageto?act=members&offset=0')
    r = requests.get(url)
    return r.text

def get_total_pages(get_html):
    soup = BeautifulSoup(get_html, 'lxml')
    pages = soup.find('div', class_='pagination').find_all('a', class_='pg_link')[-1].get('href')
    total_pages = pages.split('=')[2]
    return int(total_pages)

def main():
    base_url = 'https://m.vk.com/bageto?act=members&offset='`enter code here`
    total_pages = get_total_pages(get_html)
    for i in range(50, total_pages, 50):
        print (i)

这将产生以下错误：

C:\Users\PANDEMIC\Desktop\Python-Test>vkp.py Traceback (most recent call last):
File "C:\Users\PANDEMIC\Desktop\Python-Test\vkp.py",
line 23, in <module>
    main()
File "C:\Users\PANDEMIC\Desktop\Python-Test\vkp.py", line 20, in main
    total_pages = get_total_pages(get_html)
File "C:\Users\PANDEMIC\Desktop\Python-Test\vkp.py", line 13, in get_total_pages
    soup = BeautifulSoup(get_html, 'lxml')
File "C:\Users\PANDEMIC\AppData\Local\Programs\Python\Python36-32\lib\site-packages\bs4\__init__.py", line 192, in __init__
    elif len(markup) <= 256 and (
TypeError: object of type 'function' has no len()

C:\Users\popularity\Desktop\Python Test>vkp.py回溯（最后一次调用）：
文件“C:\Users\popularity\Desktop\Python Test\vkp.py”，
第23行，在
main（）
文件“C:\Users\popularity\Desktop\Python Test\vkp.py”，主目录第20行
总页数=获取总页数（获取html）
文件“C:\Users\popularity\Desktop\Python Test\vkp.py”，第13行，在get\u total\u页面中
soup=BeautifulSoup（获取html“lxml”）
文件“C:\Users\popularity\AppData\Local\Programs\Python\Python36-32\lib\site packages\bs4\\uuuuuu init\uuuuu.py”，第192行，在\uuu init中__
elif len（markup）在中执行
get_html（）
时忘记了
（）
和参数

total_pages = get_total_pages( get_html(base_url) )


顺便说一句：您不需要
get\u html
中的
url
，因为它将在下次调用中写入您的参数

def get_html(url):
    #url = ('https://m.vk.com/bageto?act=members&offset=0')
    r = requests.get(url)
    return r.text

也可以使用默认值

def get_html(url='https://m.vk.com/bageto?act=members&offset=0')
    r = requests.get(url)
    return r.text

完整版本，以
base\u url+“0”作为
get\u html（base\u url+“0”）中的参数

您应该将html字符串传递给BeautifulSoup，而不是函数。
在
get_html（）
中执行
get_html（）
get_total_pages（get_html（））
def main（）：try:base_url=''total_pages=int（get_total_pages（get_html（'））时，对于范围内的i（50，total_pages，50）：url_gen=base_url+str（i）print）（url_gen）键盘中断除外：print（‘您自己停止编写脚本’）main（）
def main():
    try:
        urll = []
        base_url = 'https://m.vk.com/bageto?act=members&offset='
        total_pages = int(get_total_pages(get_html(url)))
        for i in range(0, total_pages, 50):
            url_gen = str(base_url + str(i))
            urll.append(url_gen)
            #get_page_data(url_gen)
        pool = ThreadPool(8)
        results = pool.map(get_page_data, urll)

    except KeyboardInterrupt:
        print('you are stopped script yourself')

if __name__ == '__main__':

    main()

import requests
from bs4 import BeautifulSoup


def get_html(url):
    url = ('https://m.vk.com/bageto?act=members&offset=0')
    r = requests.get(url)
    return r.text

def get_total_pages(html):

    soup            = BeautifulSoup(html, 'lxml')
    pages           = soup.find('div', class_='pagination').find_all('a', class_='pg_link')[-1].get('href')
    total_pages     = pages.split('=')[2]
    return int(total_pages)

def main():
    base_url = 'https://m.vk.com/bageto?act=members&offset=0'
    html = get_html(base_url)
    total_pages = get_total_pages(html)
    print(total_pages)

def main():
    try:
        urll = []
        base_url = 'https://m.vk.com/bageto?act=members&offset='
        total_pages = int(get_total_pages(get_html(url)))
        for i in range(0, total_pages, 50):
            url_gen = str(base_url + str(i))
            urll.append(url_gen)
            #get_page_data(url_gen)
        pool = ThreadPool(8)
        results = pool.map(get_page_data, urll)

    except KeyboardInterrupt:
        print('you are stopped script yourself')

if __name__ == '__main__':

    main()