第八节：爬取新浪微博

本页代码可以在这里下载。

1.分析请求

打开新浪微博，过滤Ajax请求并查看。

我们可以看到URL中有4个属性值，分别是type、value、containerid和page，其中containerid不过是107603加上uid，page是改变的值。

2.分析响应

我们发现响应数据都在data下，其中cardlistInfo是存储微博总数等属性，cards包含了10条微博的信息。

然后我们观察请求头部分，并找出最小有效子集（一般是cookies、ua、host、referer）
然后自定义头。

headers = {
    'Host': 'm.weibo.cn',
    'Referer': 'https://m.weibo.cn/u/2656260571',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/'
                  '67.0.3396.99 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest'
}

首先获取页面json：

# get page code
def get_page(page):
    params = {
        'type': 'uid',
        'value': '2656260571',
        'containerid': '1076032656260571',
        'page': page
    }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url=url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error', e.args)

随后处理这些json，提取出需要的信息：

# parse the code
def parse_page(json):
    if json:
        items = json.get('data').get('cards')
        for item in items:
            item = item.get('mblog')
            weibo = {}
            weibo['id'] = item['id']
            weibo['text'] = item['text']
            weibo['attitudes'] = item['attitudes_count']
            weibo['comment'] = item['comments_count']
            weibo['reposts'] = item['reposts_count']
            yield weibo

存入数据库：

# save to database
def save_to_mongo(result):
    client = pymongo.MongoClient(host='localhost', port=27017)
    db = client.WeiBoTest
    collection = db.WeiBo
    collection.insert(result)

主函数调用：

# main
if __name__ == '__main__':
    for page in range(1, 15):
        json = get_page(page)
        results = parse_page(json)
        for result in results:
            print(result)
            print()
            save_to_mongo(result)

 
运行结果：
console中：

Robo 3T中：

 
完整代码：

# -*- coding:utf-8 -*-
from urllib.parse import urlencode
import pymongo
import requests
base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
    'Host': 'm.weibo.cn',
    'Referer': 'https://m.weibo.cn/u/2656260571',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/'
                  '67.0.3396.99 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest'
}
# get page code
def get_page(page):
    params = {
        'type': 'uid',
        'value': '2656260571',
        'containerid': '1076032656260571',
        'page': page
    }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url=url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error', e.args)
# parse the code
def parse_page(json):
    if json:
        items = json.get('data').get('cards')
        for item in items:
            item = item.get('mblog')
            weibo = {}
            weibo['id'] = item['id']
            weibo['text'] = item['text']
            weibo['attitudes'] = item['attitudes_count']
            weibo['comment'] = item['comments_count']
            weibo['reposts'] = item['reposts_count']
            yield weibo
# save to database
def save_to_mongo(result):
    client = pymongo.MongoClient(host='localhost', port=27017)
    db = client.WeiBoTest
    collection = db.WeiBo
    collection.insert(result)
# main
if __name__ == '__main__':
    for page in range(1, 15):
        json = get_page(page)
        results = parse_page(json)
        for result in results:
            print(result)
            print()
            save_to_mongo(result)

 
.