爬虫实战8：爬取微博内容信息_爬虫 见微

获取微博大V账号的用户基本信息，如：微博昵称、微博地址、微博头像、关注人数、粉丝数、性别、等级等

# -*- coding: utf-8 -*-
import urllib.request
import json

id = '1259110474'
proxy_addr = "122.241.72.191:808"


def use_proxy(url, proxy_addr):
    req = urllib.request.Request(url)
    req.add_header(
        "User-Agent",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
    proxy = urllib.request.ProxyHandler({'http': proxy_addr})
    opener = urllib.request.build_opener(proxy, urllib.request.HTTPHandler)
    urllib.request.install_opener(opener)
    data = urllib.request.urlopen(req).read().decode('utf-8', 'ignore')
    # print(data)
    return data


def get_containerid(url):
    data = use_proxy(url, proxy_addr)
    content = json.loads(data).get('data')
    for data in content.get('tabsInfo').get('tabs'):
        if(data.get('tab_type') == 'weibo'):
            containerid = data.get('containerid')
    return containerid

def get_userInfo(id):
    global name
    url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + id
    data = use_proxy(url, proxy_addr)
    content = json.loads(data).get('data')
    profile_image_url = content.get('userInfo').get('profile_image_url')
    description = content.get('userInfo').get('description')
    profile_url = content.get('userInfo').get('profile_url')
    verified = content.get('userInfo').get('verified')
    guanzhu = content.get('userInfo').get('follow_count')
    name = content.get('userInfo').get('screen_name')
    fensi = content.get('userInfo').get('followers_count')
    gender = content.get('userInfo').get('gender')
    urank = content.get('userInfo').get('urank')
    print(
        "微博昵称：" + name + "\n" +
        "微博主页地址：" + profile_url + "\n" +
        "微博头像地址：" + profile_image_url + "\n" +
        "是否认证：" + str(verified) + "\n" +
        "微博说明：" + description + "\n" +
        "关注人数：" + str(guanzhu) + "\n" +
        "粉丝数：" + str(fensi) + "\n" +
        "性别：" + gender + "\n" +
        "微博等级：" + str(urank) + "\n")


# 获取微博内容信息,并保存到文本中，内容包括：每条微博的内容、微博详情页面地址、点赞数、评论数、转发数等


def get_weibo(id, file):
    i = 1
    while True:
        url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + id
        weibo_url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + \
            id + '&containerid=' + get_containerid(url) + '&page=' + str(i)
        try:
            data = use_proxy(weibo_url, proxy_addr)
            content = json.loads(data).get('data')
            cards = content.get('cards')
            if len(cards) > 0:
                for j in range(len(cards)):
                    print("-----正在爬取第" + str(i) + "页，第" + str(j) + "条微博------")
                    card_type = cards[j].get('card_type')
                    if card_type == 9:
                        mblog = cards[j].get('mblog')
                        attitudes_count = mblog.get('attitudes_count')
                        comments_count = mblog.get('comments_count')
                        created_at = mblog.get('created_at')
                        reposts_count = mblog.get('reposts_count')
                        scheme = cards[j].get('scheme')
                        text = mblog.get('text')
                        with open(file, 'a', encoding='utf-8') as fh:
                            fh.write(
                                "----第" + str(i) + "页，第" + str(j) + "条微博----" + "\n")
                            fh.write(
                                "微博地址：" + str(scheme) + "\n" +
                                "发布时间：" + str(created_at) + "\n" +
                                "微博内容：" + text + "\n" +
                                "点赞数：" + str(attitudes_count) + "\n" +
                                "评论数：" + str(comments_count) + "\n" +
                                "转发数：" + str(reposts_count) + "\n")
                i += 1
            else:
                break
        except Exception as e:
            print(e)
            pass


if __name__ == "__main__":
    file = id + ".txt"
    get_userInfo(id)
    get_weibo(id, file)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103