统计网友活动的python程序。邻兄拒不跟帖，放在这里当做存根，须用的请自用 nearby2022-08-28 19:05:42

# Author: 书香之家版主 nearby, August 2022
#
# This program allows you to analyze the activities of all the users in a WXC 论坛, for example, 书香之家(sxsj).
# It counts the numbers of 主帖 and 跟帖 respectively for each user.
# The result is printed into a .CSV file. Note, to view the Chinese characters, CSV file is not good.
# So, you can view the result using Notepad or other text editor and then copy/paste the result into an Excel file.
#
#

import requests

# users: a dictionary. key=username, value = list. Inside the list, the first element is the number of 主帖
# the second element is the number of 跟帖
def processOneFile(us_dict, html):
    all = html.text.split('\n')
    length = len(all)
    i = 0
    while i < length:
        line = all[i].strip()
        jump = 6
        if line == '<!--   -->':
            i = i + 1
            line = all[i].strip()
            if line == '<!-- 列表中插广告 -->':
                jump = 9
            i = i + jump
            # print(all[i].strip())
            # this is a 主帖. get the user name first
            i = i + 3
            # the line looks like: <a class="b" href="https://passport.wenxuecity.com/members/index.php?act=profile&amp;cid=ling_yin_shi">ling_yin_shi</a>
            user = all[i].strip().split('>')[1].split('<')[0]
            # add one for this user on his or her 主帖
      if user in us_dict:
                L = us_dict[user]
                L[0] = L[0] + 1
            else:
                L = [1,0]
                us_dict[user] = L
            # Now, process on the 跟帖
            i = i + 1
            line = all[i].strip()
            while line != '</div>':
                # target this line: <a class="b"  href="https://passport.wenxuecity.com/members/index.php?act=profile&amp;cid=FionaRawson">FionaRawson</a> -
                if line.startswith('<a class="b"  href='):
                    sub_user = line.split('>')[1].split('<')[0]
                    # add one for this user on his/her 跟帖. Here, the guanshui variable is used.
                    if sub_user != user or guanshui == False:
                        if sub_user in us_dict:
                            L = us_dict[sub_user]
                            L[1] = L[1] + 1
                        else:
                            L = [0, 1]
                            us_dict[sub_user] = L
                i = i + 1
                line = all[i].strip()

        i = i + 1



# ---- main starts here ----

print()
print('# Author: 书香之家版主 nearby, August 2022')
print()

subid = 'sxsj'
temp = input('What is the name of your 论坛 in English? For example, 书香之家 is sxsj, 美语世界 is mysj, 文化走廊 is culture, 诗词欣赏 is poetry: ')
if len(temp) >= 2:
    subid = temp

numPages = 200
temp = input('How many pages you would like to search? If do not know, just hit ENTER, the program will search for 200 pages by default. ')
if len(temp) >= 1:
    numPages = int(temp)

guanshui = False # Use this variable because of kirn's talking about 灌水 :-)
temp = input('Discard those 跟帖 that a user made after his/her own post? (1=yes, 0=no, default=0)\n' +
             'Sometimes a user only post 跟帖 after his/her own 主帖. If yes, then such 跟帖 will be discarded.  ')
if int(temp) > 0:
    guanshui = True

print('guanshui='+str(guanshui))

users = dict()
for i in range(1, numPages+1):
    url = 'https://bbs.wenxuecity.com/' + subid + '/?page=' + str(i)
    f = requests.get(url)
    processOneFile(users, f)

print("\n---------------\n")
ks = users.keys()
html2 = open('sxzj-out.csv', 'w', encoding='utf-8')
for u in ks:
    L = users[u]
    print(u + ',' + str(L[0]) + ',' + str(L[1]))
    html2.write(u + ',' + str(L[0]) + ',' + str(L[1]) + '\n')
html2.close()
print("\n")
print("\n")
print("Please check the file sxzj-out.csv. The result is in it! Thanks for using this program. ---- 虎哥 / Nearby / 邻兄")