meetup爬取群组用户活动的方法

该代码可以爬取用户的个人信息（主要包括城市，爱好，参与的群组）、群组的详细信息和发布活动的参与活动。API版本后续会发布，感谢关注
```python
import csv
import requests
from bs4 import BeautifulSoup
header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'}
'''
此处的循环就是一个用户一个用户进行的操作，循环的范围就是用户的id号
也可以用过postman软件直接申请访问，或者调用meetup专门给开发人员的api也可
'''
for i in range(40000,50000):
    print('i=', i)
    id = i
    try:
        url = 'https://www.meetup.com/members/' + str(i) + '/'
        r = requests.get(url, headers=header)#无法获取url的源码就推出
    except:
        continue
#若成功获取网页源码，则开始解析
    soup = BeautifulSoup(r.text, 'html.parser')
    client_data = []
    # id√
    id = i
    # 用户名√
    try:
        interests_mid = soup.find('li', class_="D_group small last").div.find_all('a')
        interests = []
        for k in range(0, len(interests_mid)):
            interests.append(interests_mid[k].text.strip())
        name = soup.find('h1', class_="flush--bottom text--display3").span.string
        position = soup.find('div', class_="D_memberProfileContentItem").p.a.span.string
    except:
        continue
    # 兴趣
    client_data.append(id)
    client_data.append(name)
    client_data.append(position)
    client_data.append(interests)
    group1_len = 1
    group2_len = 1
    group3_len = 1
    try:
        group1 = soup.find_all('div', class_="D_group clearfix first groupinfo-widget")
    except:
        group1_len = 0
    try:
        group2 = soup.find_all('div', class_="D_group clearfix groupinfo-widget")
    except:
        group2_len = 0
    try:
        group3 = soup.find_all('div', class_="D_group clearfix display-none groupinfo-widget")
    except:
        group3_len = 0
    if group1_len+group2_len+group3_len == 0:
        continue#未参与任何群组的用户不统计
    group = group1 + group2 + group3  # 用户参与的群组
    group_join = []  # 参与的群组名称
    group_join1 = []
    group_join_web = []  # 参与的群组的网址
    for s in range(0, len(group)):#搜集群组无误，开始找到每个群组元素的群组名称和网站
        try:
            group_join.append(
                group[s].find('div', class_="figureset-description margin-bottom").h4.a.text.strip())
            group_join_web.append(group[s].find('div', class_="figureset-description margin-bottom").h4.a['href'])
        except:#找不到参与的群组,就放弃该群组往下找
            continue
    if len(group_join_web)==0:
        continue#用户确确实实参与了群组，但是爬虫无法找到群组的信息，则直接跳过，同样忽略该用户，进行下一个id的信息爬取
    group_join1 = group_join.copy()
    for k in range(0, len(group_join_web)):
        group_data = []
        url = group_join_web[k]
        try:
            r = requests.get(url, headers=header)
            soup = BeautifulSoup(r.text, 'html.parser')
            group_intro = soup.find('span', class_="infoToggle-label").text.strip() + '|' + soup.find('div',
                                                                                                      class_="group-description--wrapper").text.strip()
            group_posi = soup.find('ul', class_="organizer-city").a.span.text.strip()
            # 群组位置
            r = requests.get(group_join_web[k] + 'events/past/', headers=header)
            soup = BeautifulSoup(r.text, 'html.parser')
            activity = []
            activity1 = []
            activity_web = soup.find_all('li', class_="list-item border--none")
            if len(activity_web) == 0:  # 找不到群组发布的活动就跳过，因为没有发布活动或者发布不全的活动数据没有用
                continue
            for i1 in range(0, len(activity_web)):
                activity.append(activity_web[i1].find('a', class_="eventCardHead--title").text.strip())
            activity1 = activity.copy()
            group_data.append(group_join[k])  # 群组
            group_data.append(group_join_web[k])  # 群组网站
            group_data.append(group_posi)  # 群组位置
            group_data.append(group_intro)  # 群组介绍
            for k1 in range(0, len(activity_web)):
                activity_data = []
                try:
                    p_all = activity_web[k1].find_all('p', class_="text--small padding--top margin--halfBottom")
                    activity_detail = p_all[1].text.strip()
                    activity_date = activity_web[k1].find('span', class_="eventTimeDisplay-startDate").text
                except:
                    activity1.remove(activity[k1])
                    continue
                try:
                    activity_position = activity_web[k1].find('p',
                                                              class_="venueDisplay venueDisplay-venue-locationHidden padding--left-half text--secondary text--small").span.text.strip()
                except AttributeError:
                    try:
                        activity_position = activity_web[k1].find('div',
                                                                  class_="venueDisplay venueDisplay-venue padding--left-half text--secondary text--small").address.p.text.strip()
                    except AttributeError:
                        try:
                            activity_position = activity_web[k1].find('p',
                                                                      class_="venueDisplay venueDisplay-venue-noVenue padding--left-half text--secondary text--small").span.text.strip()
                        except AttributeError:
                            activity1.remove(activity[k1])
                            continue
                activity_data.append(group_join[k])
                activity_data.append(activity[k1])
                activity_data.append(activity_date)
                activity_data.append(activity_position)
                activity_data.append(activity_detail)
                with open("activity_data.csv", 'a', newline='', encoding="utf-8") as f:
                    writer = csv.writer(f)
                    writer.writerow(activity_data)
                    f.close()
            if len(activity1)==0:
                group_join1.remove(group_join[k])
                continue
            group_data.append(activity1)  # 群组活动
            with open("group_data.csv", 'a', newline='', encoding="utf-8") as f:
                writer = csv.writer(f)
                writer.writerow(group_data)
                f.close()
        except:
            group_join1.remove(group_join[k])
            continue
    if len(group_join1)==0:
        continue
    client_data.append(group_join1)
    with open("client_data.csv", 'a', newline='', encoding="utf-8") as f:  # 确认无误，存入用户数据
        writer = csv.writer(f)
        writer.writerow(client_data)
        f.close()
    # 此处写入文件,且成功爬取了所有的用户信息和对应的群组网址