如何抓取 Google Trends 数据：完整实用指南（2026）

from pytrends.request import TrendReq


# Initialize — hl sets the language, tz sets the timezone offset

pytrends = TrendReq(hl='en-US', tz=360)


# Build the payload — specify up to 5 keywords here

pytrends.build_payload(

    kw_list=['artificial intelligence'],

    timeframe='today 12-m',

    geo=''  # Empty string = worldwide

)

# Pull interest over time

data = pytrends.interest_over_time()

print(data.head(10))

data = data[data['isPartial'] == False]

from pytrends.request import TrendReq

pytrends = TrendReq(hl='en-US', tz=360)

pytrends.build_payload(

    kw_list=['ChatGPT', 'Gemini', 'Claude AI', 'Copilot'],

    timeframe='today 12-m',

    geo='US'

)

data = pytrends.interest_over_time()

data = data[data['isPartial'] == False]

# Which platform has the highest average interest?

print(data[['ChatGPT', 'Gemini', 'Claude AI', 'Copilot']].mean())

pytrends.build_payload(

    kw_list=['electric vehicles'],

    timeframe='today 12-m'

)




# Country-level interest

by_country = pytrends.interest_by_region(resolution='COUNTRY', inc_low_vol=True)




# Sort by interest descending

print(by_country.sort_values('electric vehicles', ascending=False).head(20))

by_state = pytrends.interest_by_region(resolution='REGION', geo='US')

python

pytrends.build_payload(

    kw_list=['remote work tools'],

    timeframe='today 3-m'

)




related = pytrends.related_queries()




# Rising queries — growing fastest relative to their usual volume

print(related['remote work tools']['rising'])




# Top queries — highest absolute interest

print(related['remote work tools']['top'])

trending_today = pytrends.trending_searches(pn='united_states')

print(trending_today.head(20))

import requests

import json




session = requests.Session()




# First, establish a session by visiting the main Trends page

session.get('https://trends.google.com/')




# The explore endpoint generates widget tokens for data requests

params = {

    'hl': 'en-US',

    'tz': '-360',

    'req': json.dumps({

        "comparisonItem": [

            {"keyword": "python programming", "geo": "", "time": "today 12-m"}

        ],

        "category": 0,

        "property": ""

    }),

    'token': '',

    'user_type': ''

}




response = session.get(

    'https://trends.google.com/trends/api/explore',

    params=params

)




# Strip the protection prefix before parsing

clean_response = response.text.lstrip(")}']\n")

data = json.loads(clean_response)

from playwright.sync_api import sync_playwright

import time




with sync_playwright() as p:

    # Launch browser — headless=False for debugging, True for production

    browser = p.chromium.launch(headless=True)

    

    # Create a context with realistic browser settings

    context = browser.new_context(

        user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',

        viewport={'width': 1280, 'height': 800}

    )

    

    page = context.new_page()

    

    # Navigate to Trends

    page.goto('https://trends.google.com/trends/explore?q=python+programming&date=today+12-m&geo=US')

    

    # Wait for the data chart to render

    page fully

.wait_for_selector('[class*="widget"]', timeout=10000)

    

    # Add human-like delay

    time.sleep(3)

    

    # Extract page content for parsing

    content = page.content()

    

    # Alternatively, intercept the API response directly

    # This is more reliable than parsing HTML

    

    browser.close()




print("Data extracted successfully")

import time

from pytrends.request import TrendReq




pytrends = TrendReq(hl='en-US', tz=360)




keywords = [

    'content marketing', 'SEO strategy', 'link building',

    'technical SEO', 'keyword research', 'on-page SEO'

]




results = {}




for keyword in keywords:

    pytrends.build_payload([keyword], timeframe='today 12-m')

    results[keyword] = pytrends.interest_over_time()

    print(f"✓ {keyword}")

    time.sleep(15)  # 15 seconds between requests




print("All keywords retrieved.")

from pytrends.request import TrendReq

import time

import random




# CyberYozh proxy configuration

proxy_config = {

    'https': 'https://USERNAME:PASSWORD@gate.cyberyozh.com:PORT'

}




# Initialize pytrends with proxy support

pytrends = TrendReq(

    hl='en-US',

    tz=360,

    requests_args={

        'proxies': proxy_config,

        'verify': True

    }

)




keywords = ['machine learning', 'deep learning', 'neural networks',

            'computer vision', 'natural language processing']




for keyword in keywords:

    pytrends.build_payload([keyword], timeframe='today 12-m', geo='US')

    data = pytrends.interest_over_time()

    print(f"Retrieved: {keyword} — {len(data)} weeks of data")

    time.sleep(random.uniform(8, 20))  # Randomize delays to mimic human behavior

python

from playwright.sync_api import sync_playwright




with sync_playwright() as p:

    browser = p.chromium.launch(

        headless=True,

        proxy={

            "server": "https://gate.cyberyozh.com:PORT",

            "username": "USERNAME",

            "password": "PASSWORD"

        }

    )

    # ... rest of automation code

from pytrends.request import TrendReq

import pandas as pd

import time




pytrends = TrendReq(hl='en-US', tz=360)




# Batch 1: Compare keyword sets against anchor

batch_1 = ['Facebook', 'content marketing', 'email marketing', 'social media marketing']

batch_2 = ['Facebook', 'SEO', 'PPC advertising', 'influencer marketing']




pytrends.build_payload(batch_1, timeframe='today 12-m', geo='US')

data_1 = pytrends.interest_over_time()[batch_1]




time.sleep(15)




pytrends.build_payload(batch_2, timeframe='today 12-m', geo='US')

data_2 = pytrends.interest_over_time()[batch_2]




# Now normalize both datasets against the anchor (facebook)

# The anchor's values are comparable across batches because they were in both

anchor = 'facebook'




data_1_normalized = data_1.div(data_1[anchor], axis=0)

data_2_normalized = data_2.div(data_2[anchor], axis=0)




# Now you can meaningfully compare any keyword from batch 1 with any from batch 2

print("Normalized comparison:")

print(pd.concat([

    data_1_normalized.drop(columns=[anchor]),

    data_2_normalized.drop(columns=[anchor])

], axis=1).mean())

from pytrends.request import TrendReq

import matplotlib.pyplot as plt

import pandas as pd




pytrends = TrendReq(hl='en-US', tz=360)

pytrends.build_payload(

    ['AI tools', 'automation software'],

    timeframe='today 5-y',

    geo='US'

)




data = pytrends.interest_over_time()

data = data[data['isPartial'] == False]




# Export to CSV for spreadsheet analysis

data.to_csv('google_trends_export.csv')

print("CSV exported successfully.")




# Create a clean visualization

fig, ax = plt.subplots(figsize=(14, 6))




data['AI tools'].plot(ax=ax, label='AI Tools', color='#2563EB', linewidth=2)

data['automation software'].plot(ax=ax, label='Automation Software', color='#7C3AED', linewidth=2)




ax.set_title('Search Interest Comparison: AI Tools vs Automation Software (5 Years, US)', 

             fontsize=14, fontweight='bold', pad=20)

ax.set_ylabel('Interest Score (0–100)', fontsize=11)

ax.set_xlabel('')

ax.legend(fontsize=11)

ax.grid(True, alpha=0.3)

ax.set_ylim(0, 110)




plt.tight_layout()

plt.savefig('trends_comparison.png', dpi=150, bbox_inches='tight')

plt.show()