python爬取谷歌数据 python爬虫之爬取谷歌趋势数据

import socket
import socks
import requests
import json
import pandas as pd
import logging

#加入socks5代理后，可以获得当前程序的全局代理
socks.set_default_proxy(socks.SOCKS5,"127.0.0.1",1080)
socket.socket = socks.socksocket

#加入以下代码，否则会出现InsecureRequestWarning警告，虽然不影响使用，但看着糟心
# 捕捉警告
logging.captureWarnings(True)
# 或者加入以下代码，忽略requests证书警告
# from requests.packages.urllib3.exceptions import InsecureRequestWarning
# requests.packages.urllib3.disable_warnings(InsecureRequestWarning)

# 将三个页面获得的数据存为DataFrame
time_trends = pd.DataFrame()
related_topic = pd.DataFrame()
related_search = pd.DataFrame()

#填入自己打开网页的请求头
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36',
    'x-client-data': 'CJa2yQEIorbJAQjEtskBCKmdygEI+MfKAQjM3soBCLKaywEI45zLAQioncsBGOGaywE=Decoded:message ClientVariations {// Active client experiment variation IDs.repeated int32 variation_id = [3300118, 3300130, 3300164, 3313321, 3318776, 3321676, 3329330, 3329635, 3329704];// Active client experiment variation IDs that trigger server-side behavior.repeated int32 trigger_variation_id = [3329377];}',
    'referer': 'https://trends.google.com/trends/explore',
    'cookie': '__utmc=10102256; __utmz=10102256.1617948191.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); __utma=10102256.889828344.1617948191.1617948191.1617956555.3; __utmt=1; __utmb=10102256.5.9.1617956603932; SID=8AfEx31goq255ga6Ldt9ljEVZ5xQ7fYTAdzCK3DgEYp2s6MOxeKc__hQ90tTtn0W-6AVoQ.; __Secure-3PSID=8AfEx31goq255ga6Ldt9ljEVZ5xQ7fYTAdzCK3DgEYp2s6MOLU4HYHzyoAXIvtAhfF_WNg.; HSID=AELT1m_DoHJY-r6SW; SSID=AJSlRt0T7ngXXMtqv; APISID=3Nt6oALGV8kSym2M/A2QeNBMtb9P7VcIwV; SAPISID=iAA0fu76JZezPfK4/Apws7zK1y-o74b2YD; __Secure-3PAPISID=iAA0fu76JZezPfK4/Apws7zK1y-o74b2YD; 1P_JAR=2021-04-06-06; SEARCH_SAMESITE=CgQIo5IB; NID=213=oYQE35gIVD2DrxbpY7NdAQsAEyg-If7Jh_nBdSKTkvmtgaVV7tYeSQNq_636cysbsajJP3_dKfr95w51ywK-dxVYhzPP4Zll9JndBYY98vd_XegGoeLEevpxIhNxUAv6H24OVt_edoGFkSjTpWKn4QAoIoerHCViyvozrvGF7m4scupppmxN-h9dwm1nrs15I3b_E-ifLq0lgd9s7QrgA-FRuaDeyuXN8t1K7l_DMTB1jkE5ED_dC-_QAO7DDw; SIDCC=AJi4QfFdMiK_qV41ViVJf0wWmtOu8yUVSQc_UEvemoaQwTGI9W0w2XwwkMCufVcYIS5ogRSkq5w; __Secure-3PSIDCC=AJi4QfEmB-gnzZLHWR4p1EmOfS2dhSz9zWSGNGOozrY2udFk4KwVmVo_srZdZrmdy7h_mwLSwQ'
}


# 获取需要的三个界面的req值和token值
def get_token_req(keyword):
    url = 'https://trends.google.com/trends/api/explore?hl=zh-CN&tz=-480&req={{"comparisonItem":[{{"keyword":"{}","geo":"US","time":"today 12-m"}}],"category":0,"property":""}}&tz=-480'.format(
        keyword)
    html = requests.get(url, headers=headers, verify=False).text
    data = json.loads(html[5:])

    req_1 = data['widgets'][0]['request']
    token_1 = data['widgets'][0]['token']

    req_2 = data['widgets'][2]['request']
    token_2 = data['widgets'][2]['token']

    req_3 = data['widgets'][3]['request']
    token_3 = data['widgets'][3]['token']

    result = {'req_1': req_1, 'token_1': token_1, 'req_2': req_2, 'token_2': token_2, 'req_3': req_3,
              'token_3': token_3}
    return result


# 请求三个界面的数据，返回的是json数据，所以数据不用解析，完美
def get_info(keyword):
    content = []
    keyword = keyword
    result = get_token_req(keyword)

    #第一个界面
    req_1 = result['req_1']
    token_1 = result['token_1']
    url_1 = "https://trends.google.com/trends/api/widgetdata/multiline?hl=zh-CN&tz=-480&req={}&token={}&tz=-480".format(
        req_1, token_1)
    r_1 = requests.get(url_1, headers=headers, verify=False)
    if r_1.status_code == 200:
        try:
            content_1 = r_1.content
            content_1 = json.loads(content_1.decode('unicode_escape')[6:])['default']['timelineData']
            result_1 = pd.json_normalize(content_1)
            result_1['value'] = result_1['value'].map(lambda x: x[0])
            result_1['keyword'] = keyword
        except Exception as e:
            print(e)
            result_1 = None
    else:
        print(r_1.status_code)

    #第二个界面
    req_2 = result['req_2']
    token_2 = result['token_2']
    url_2 = 'https://trends.google.com/trends/api/widgetdata/relatedsearches?hl=zh-CN&tz=-480&req={}&token={}'.format(
        req_2, token_2)
    r_2 = requests.get(url_2, headers=headers, verify=False)
    if r_2.status_code == 200:
        try:
            content_2 = r_2.content
            content_2 = json.loads(content_2.decode('unicode_escape')[6:])['default']['rankedList'][1]['rankedKeyword']
            result_2 = pd.json_normalize(content_2)
            result_2['link'] = "https://trends.google.com" + result_2['link']
            result_2['keyword'] = keyword
        except Exception as e:
            print(e)
            result_2 = None
    else:
        print(r_2.status_code)

    #第三个界面
    req_3 = result['req_3']
    token_3 = result['token_3']
    url_3 = 'https://trends.google.com/trends/api/widgetdata/relatedsearches?hl=zh-CN&tz=-480&req={}&token={}'.format(
        req_3, token_3)
    r_3 = requests.get(url_3, headers=headers, verify=False)
    if r_3.status_code == 200:
        try:
            content_3 = r_3.content
            content_3 = json.loads(content_3.decode('unicode_escape')[6:])['default']['rankedList'][1]['rankedKeyword']
            result_3 = pd.json_normalize(content_3)
            result_3['link'] = "https://trends.google.com" + result_3['link']
            result_3['keyword'] = keyword
        except Exception as e:
            print(e)
            result_3 = None
    else:
        print(r_3.status_code)

    content = [result_1, result_2, result_3]

    return content

def main():
    global time_trends,related_search,related_topic
    with open(r'C:\Users\Desktop\words.txt','r',encoding = 'utf-8') as f:
        words = f.readlines()
    for keyword in words:
        keyword = keyword.strip()
        data_all = get_info(keyword)
        time_trends = pd.concat([time_trends,data_all[0]],sort = False)
        related_topic = pd.concat([related_topic,data_all[1]],sort = False)
        related_search = pd.concat([related_search,data_all[2]],sort = False)

if __name__ == "__main__":
    main()