Python爬虫实战！爬取百度指数并可视化

海哥发现百度指数的加密方式又变了，修改了一下之前的代码。

完整代码如下。

import json
import requests
import urllib.request
from datetime import datetime
from datetime import timedelta


# 获取IP代理
def get_proxy():
    opener = urllib.request.build_opener(
        urllib.request.ProxyHandler(
            {'http': 'http://brd-customer-hl_5dede465-zone-try-country-cn:pdqt396jal8m@brd.superproxy.io:22225',
             'https': 'http://brd-customer-hl_5dede465-zone-try-country-cn:pdqt396jal8m@brd.superproxy.io:22225'}))

    response = opener.open('http://lumtest.com/myip.json').read()
    response_str = response.decode('utf-8')
    ip = json.loads(response_str)['ip']

    proxies = {
        "http": "http://{}".format(ip),
        "https": "http://{}".format(ip),
    }

    return proxies


# 解码函数
def decrypt(ptbk, index_data):
    n = len(ptbk)//2
    a = dict(zip(ptbk[:n], ptbk[n:]))
    return "".join([a[s] for s in index_data])


def reCode(data, ptbk):
    data = data['data']
    li = data['userIndexes'][0]['all']['data']
    startDate = data['userIndexes'][0]['all']['startDate']
    year_str = startDate[:4]  # 使用切片取前四个字符，即年份部分
    try:
        # 将年份字符串转换为整数
        year = int(year_str)
        # 根据年份判断是否为闰年
        if (year % 4 == 0 and year % 100 != 0) or (year % 400 == 0):
            year = 366
        else:
            year = 365
    except :
        year =365

    if li =='':
        result = {}
        name = data['userIndexes'][0]['word'][0]['name']
        tep_all = []
        while len(tep_all) < year:
            tep_all.insert(0, 0)
        result["name"] = name
        result["data"] = tep_all
    else:
        ptbk = ptbk
        result