DEV Community

Scrapfly profile image Scrapfly
Scrapfly for Scrapfly

Posted on • Originally published at scrapfly.io on

How to Scrape SimilarWeb Website Traffic Analytics

#scrapeguide #seo #searchengine

How to Scrape SimilarWeb Website Traffic Analytics

SimilarWeb is a leading platform specializing in web analytics, acting as a directory for worldwide website traffic. Imagine the insights and SEO impact would scraping SimilarWeb allow for!

In this guide, we'll explain how to scrape SimilarWeb through a step-by-step guide. We'll scrape comprehensive domain traffic insights, websites comparing data, sitemaps, and trending industry domains. Let's get started!

Latest SimilarWeb Scraper Code

This tutorial covers popular web scraping techniques for education. Interacting with public servers requires diligence and respect and here's a good summary of what not to do:

  • Do not scrape at rates that could damage the website.
  • Do not scrape data that's not available publicly.
  • Do not store PII of EU citizens who are protected by GDPR.
  • Do not repurpose the entire public datasets which can be illegal in some countries.

Scrapfly does not offer legal advice but these are good general rules to follow in web scraping and for more you should consult a lawyer.

Why Scrape SimilarWeb?

Web scraping SimilarWeb provides us with detailed valuable insights into websites' traffic, which can be valuable across different aspects.

  • Competitor Analysis

    One of the key features of web analytics is analyzing the industry peers and benchmarking against their traffic. Scraping SimilarWeb enables such data retrieval, allowing business to fine-tune their strategies to meet their competitors and gain a competitive edge.

  • SEO and Keyword Analysis

    Search Engine Optimization (SEO) is crucial for driving traffic into the domains. SimilarWeb data extraction provides comprehensive insights into the SEO keywords and search engine rankings, allowing for better online presence and visibility.

  • Data-Driven Decision Making

    The search trends are aggressive and fast-changing. Therefore, utilizing scraping SimilarWeb for data-based insights is crucial for supporting decision-making and defining strategies.

Have a look at our comprehensive guide on web scraping use cases for further details.

Setup

To web scrape SimilarWeb, we'll use Python with a few community packages.

  • httpx: To request SimilarWeb pages and get the data as HTML. Feel free to replace httpx with any other HTTP client, such as requests.
  • parsel: To parse the HTML retrieved using web selectors, such as XPath and CSS.
  • JMESPath: To refine the JSON datasets we get and remove the unnecessary details.
  • asyncio: To increase our SimilarWeb scraper speed by running it asynchronously.
  • loguru: Optional prerequisite to monitor our code through colored terminal outputs.

Since asyncio comes pre-installed in Python, we'll only have to install the other packages using the following pip command:

pip install httpx parsel jmespath loguru
Enter fullscreen mode Exit fullscreen mode

How to Discover SimilarWeb Pages?

Crawling sitemaps is a great way to discover and navigate pages on a website. Since they direct search engines for organized indexing, we can use them for scraping, too!

The SimilarWeb sitemaps can be found at similarweb.com/robots.txt, which looks like this:

User-agent: *
Disallow: */search/
Disallow: */adult/*
Disallow: /corp/*.pdf$
Disallow: /corp/solution/
Disallow: /corp/lps/
Disallow: /corp/get-data/
Disallow: /silent-login/
Disallow: /signin-oidc/
Disallow: /signout-oidc/
Sitemap: https://www.similarweb.com/corp/sitemap_index.xml
Sitemap: https://www.similarweb.com/blog/sitemap_index.xml
Sitemap: https://www.similarweb.com/sitemaps/sitemap_index.xml.gz
#
# sMMMMMMMMs
# MNdmMh+-``.:ohNM
# MNy/ .sMd- `/yNM
# MNo` sMo .oNM
# Md - sMo -dM
# 'MM+ -dMm+. yMM'
# MN` `:yNMd/ .NM
# MN- `-hMy :MM
# MMN- sMd` -NM
# Md:` `sh`` .sMM
# Mdms+-.```

-hmMds
# oMMMMMMMMo
#
# OFFICIAL MEASURE OF THE DIGITAL WORLD
#
Enter fullscreen mode Exit fullscreen mode

Each of the above sitemap indexes represents a group of related sitemaps. Let's explore the latest sitemap /sitemaps/sitemap_index.xml.gz. It's a gz compressed file to save bandwidth, which looks like this after extracting:


xml
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
    ....
    <sitemap>
        <loc>https://www.similarweb.com/sitemaps/top-websites-trending/part-00000.gz</loc>
        <lastmod>2023-08-17</lastmod>
    </sitemap>

    <sitemap>
        <loc>https://www.similarweb.com/sitemaps/website/part-00000.gz</loc>
        <lastmod>2023-08-17</lastmod>
    </sitemap>

    <sitemap>
        <loc>https://www.similarweb.com/sitemaps/website_competitors/part-00000.gz</loc>
        <lastmod>2023-08-17</lastmod>
    </sitemap>

</sitemapindex>
Enter fullscreen mode Exit fullscreen mode

We have reached another sitemap index for several website insight pages. Let's scrape SimilarWeb sitemap for the trending websites.

Python:


python
import asyncio
import json
from typing import List
from httpx import AsyncClient, Response
from parsel import Selector
from loguru import logger as log

# initialize an async httpx client
client = AsyncClient(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
    },
)

def parse_sitemaps(response: Response) -> List[str]:
    """parse links for bestbuy sitemaps"""
    # decode the .gz file
    xml = response.content.decode('utf-8')
    selector = Selector(xml)
    data = []
    for url in selector.xpath("//url/loc/text()"):
        data.append(url.get())
    return data

async def scrape_sitemaps(url: str) -> List[str]:
    """scrape link data from bestbuy sitemaps"""
    response = await client.get(url)
    urls = parse_sitemaps(response)
    log.success(f"scraped {len(urls)} urls from sitemaps")    
    return urls
Enter fullscreen mode Exit fullscreen mode

ScrapFly


python
import asyncio
import json
from typing import List
from parsel import Selector
from loguru import logger as log
from scrapfly import ScrapeConfig, ScrapflyClient, ScrapeApiResponse

SCRAPFLY = ScrapflyClient(key="Your ScrapFly API key")

def parse_sitemaps(response: ScrapeApiResponse) -> List[str]:
    """parse links for bestbuy sitemap"""
    bytes_data = response.scrape_result['content'].getvalue()
    # decode the .gz file
    xml = bytes_data.decode('utf-8')
    selector = Selector(xml)
    data = []
    for url in selector.xpath("//url/loc/text()"):
        data.append(url.get())
    return data

async def scrape_sitemaps(url: str) -> List[str]:
    """scrape link data from bestbuy sitemap"""
    response = await SCRAPFLY.async_scrape(ScrapeConfig(url, asp=True, country="US"))
    urls = parse_sitemaps(response)
    log.success(f"scraped {len(urls)} urls from sitemaps")
    return urls
Enter fullscreen mode Exit fullscreen mode

Run the code:


python
async def run():
    urls = await scrape_sitemaps(
        url="https://www.similarweb.com/sitemaps/top-websites-trending/part-00000.gz"
    )
    # save the data to a JSON file
    with open("sitemap_urls.json", "w", encoding="utf-8") as file:
        json.dump(urls, file, indent=2, ensure_ascii=False)

if __name__ == " __main__":
    asyncio.run(run())
Enter fullscreen mode Exit fullscreen mode

In the above code, we define an httpx client with basic browser headers to avoid blocking and define two functions. Let's break them down:

  • parse_sitemaps: For parsing the URLs inside the XML file after extracting it.
  • scrape_sitemaps: for requesting the sitemap URL while utilizing the parsing logic.

The above code will save more than 10,000 URLs to the sitemap_urls.json file. Here's an example output:


json
[
  "https://www.similarweb.com/top-websites/food-and-drink/groceries/trending/",
  "https://www.similarweb.com/top-websites/gambling/bingo/trending/",
  "https://www.similarweb.com/top-websites/travel-and-tourism/transportation-and-excursions/trending/",
  "https://www.similarweb.com/top-websites/health/health-conditions-and-concerns/trending/",
  "https://www.similarweb.com/top-websites/finance/investing/trending/",
  ....
]
Enter fullscreen mode Exit fullscreen mode

The above URLs represent website ranking pages for different industries. Let's scrape them next!

For further details on scraping sitemaps, refer to our dedicated guide.

How to Scrape SimilarWeb Trending Websites?

The trending website pages on SimilarWeb represent two related insights:

  • Trending: The month's trending websites and their traffic changes.
  • Ranking: The industry's overall website rankings with essential traffic insights.

Let's scrape the trending website section. Go to any industry trending page, such as the one for software, and you will get a similar web page:

How to Scrape SimilarWeb Website Traffic Analytics
Website rankings on SimilarWeb

We can parse the above SimilarWeb page using selectors to scrape it. However, there is a better approach: hidden web data.

To locate the website ranking hidden web data, follow the below steps:

  • Open the browser developer tools by clicking the F12 key.
  • Search for the XPath selector: //script[@id='dataset-json-ld'].

After following the above steps, you will find the below data:

How to Scrape SimilarWeb Website Traffic Analytics

The above data is the same on the web page but before getting rendered into the HTML. To scrape it, we'll select its associated script tag and then parse it.

Python:


python
import asyncio
import json
from typing import List, Dict
from httpx import AsyncClient, Response
from parsel import Selector
from loguru import logger as log

# initialize an async httpx client
client = AsyncClient(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br"
    },
)

def parse_trending_data(response: Response) -> List[Dict]:
    """parse hidden trending JSON data from script tags"""
    selector = Selector(response.text)
    json_data = json.loads(selector.xpath("//script[@id='dataset-json-ld']/text()").get())["mainEntity"]
    data = {}
    data["name"] = json_data["name"]
    data["url"] = str(response.url)
    data["list"] = json_data["itemListElement"]
    return data

async def scrape_trendings(urls: List[str]) -> List[Dict]:
    """parse trending websites data"""
    to_scrape = [client.get(url) for url in urls]
    data = []
    for response in asyncio.as_completed(to_scrape):
        response = await response    
        category_data = parse_trending_data(response)
        data.append(category_data)
    log.success(f"scraped {len(data)} trneding categories from similarweb")
    return data
Enter fullscreen mode Exit fullscreen mode

ScrapFly


python
import asyncio
import json
from typing import List, Dict
from loguru import logger as log
from scrapfly import ScrapeConfig, ScrapflyClient, ScrapeApiResponse

SCRAPFLY = ScrapflyClient(key="Your ScrapFly API key")

def parse_trending_data(response: ScrapeApiResponse) -> List[Dict]:
    """parse hidden trending JSON data from script tags"""
    selector = response.selector
    json_data = json.loads(selector.xpath("//script[@id='dataset-json-ld']/text()").get())["mainEntity"]
    data = {}
    data["name"] = json_data["name"]
    data["url"] = response.scrape_result["url"]
    data["list"] = json_data["itemListElement"]
    return data

async def scrape_trendings(urls: List[str]) -> List[Dict]:
    """parse trending websites data"""
    to_scrape = [ScrapeConfig(url, asp=True, country="US") for url in urls]
    data = []
    async for response in SCRAPFLY.concurrent_scrape(to_scrape):
        category_data = parse_trending_data(response)
        data.append(category_data)
    log.success(f"scraped {len(data)} trneding categories from similarweb")
    return data
Enter fullscreen mode Exit fullscreen mode

Run the code:


python
async def run():
    data = await scrape_trendings(
        urls=[
            "https://www.similarweb.com/top-websites/computers-electronics-and-technology/programming-and-developer-software/",
            "https://www.similarweb.com/top-websites/computers-electronics-and-technology/social-networks-and-online-communities/",
            "https://www.similarweb.com/top-websites/finance/investing/"
        ]
    )
    # save the data to a JSON file
    with open("trendings.json", "w", encoding="utf-8") as file:
        json.dump(data, file, indent=2, ensure_ascii=False)

if __name__ == " __main__":
    asyncio.run(run())
Enter fullscreen mode Exit fullscreen mode

We use the previously defined httpx client and define additional functions:

  • parse_trending_data: For extracting the page JSON data from the hidden script tag, organizing the data by removing the JSON schema details and adding the URL.
  • scrape_trendings: For adding the page URLs to a list and requesting them concurrently.

Here is a sample output of the above SimilarWeb scraping code:


json
[
  {
    "name": "Most Visited Social Media Networks Websites",
    "url": "https://www.similarweb.com/top-websites/computers-electronics-and-technology/social-networks-and-online-communities/",
    "list": [
      {
        "@type": "ListItem",
        "position": 1,
        "item": {
          "@type": "WebSite",
          "name": "facebook.com",
          "url": "https://www.similarweb.com/website/facebook.com/"
        }
      },
      ....
    ]
  },
  ....
]
Enter fullscreen mode Exit fullscreen mode

Next, let's explore the exciting part of our SimilarWeb scraper: website analytics! But before this, we must solve a SimilarWeb scraping blocking issue: validation challenge.

How to Avoid SimilarWeb Validation Challenge?

The SimilarWeb validation challenge is a web scraping blocking mechanism that blocks HTTP requests from clients without JavaScript support. It's a JavaScript challenge that's automatically bypassed after 5 seconds when requesting the domain for the first time:

How to Scrape SimilarWeb Website Traffic Analytics
SimilarWeb scraping blocking: request processing

Since we scrape SimilarWeb with an HTTP client that doesn't support JavaScript (httpx), requests sent to pages with this challenge will be blocked due to not evaluating it:


python
from httpx import Client

client = Client(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
    },
)

response = client.get("https://www.similarweb.com/website/google.com/")
print(response.text)
"""
<!DOCTYPE html><html><head><meta charset="utf-8">
<title>Challenge Validation</title>
<script type="text/javascript">function cp_clge_done(){location.reload(true);}</script>
<script src="/_sec/cp_challenge/sec-cpt-int-4-3.js" async defer></script>
<script type="text/javascript">sessionStorage.setItem('data-duration', 5);</script>
</html>
"""
Enter fullscreen mode Exit fullscreen mode

To avoid the SimilarWeb validation challenge, we can use a headless browser to complete the challenge automatically using JavaScript. However, there's a trick we can use to bypass the challenge without JavaScript: cookies!

When the validation challenge is solved, the website cookies are updated with the challenge state, so it's not triggered again.

We can make use of cookies for web scraping to bypass the validation challenge automatically! To do this, we have to get the cookie value:

  • Go to any protected SimilarWeb page with the challenge.
  • Open the browser developer tools by pressing the F12 key.
  • Select the Application tab and choose cookies.
  • Copy the _abck cookie value, which is responsible for the challenge.

After following the above steps, you will find the SimilarWeb saved cookies:

How to Scrape SimilarWeb Website Traffic Analytics
SimilarWeb cookies

Adding the _abck cookie to the requests will authorize them against the challenge:


python
from httpx import Client

client = Client(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
        "Cookie": "_abck=85E72C5791B36ED327B311F1DC7461A6~0~YAAQHPR6XIavCzyOAQAANeDuYgs83VF+IZs6MdB2WGsdsp5d89AWqe1hI+IskJ6V24OYvokUZSIn2Om9PATl5rqminoOTHQYZAMWO5Om8bcXlT3q2D9axmG+YQkS/77h/7O98vFFDrFX8Jns/upO+RbomHm7SxQ0IGk0yS80GGbWBQoSkxN+770ltBb9vdyT/7ShUBl3eKz/iLfyMSe4SyOxymE0pQL0pch0FJhvCiC2CD4asMBXGBNMQv2qvA553uO9bwz4Yr1X/7zLPOm6Vn2bz242O7rephGPmVud25Yc3Khs0oEqiQ4pgMvCy/NGIXTlVKN8anBc5QlnqGw7dq8kLqDrID9HqzbqusS9p5gkNUd4A2QJXDj80pjB9k4SWitpn1zRhsUNUYzrfvHMeGiDZhNuTYSq3sMcYg==~-1~-1~-1"
    },
)

response = client.get("https://www.similarweb.com/website/google.com/")
print(response.text) # full HTML response
Enter fullscreen mode Exit fullscreen mode

We can successfully bypass the validation challenge. However, the cookie value has to be rotated as it can expire. The rotation logic can also be automated with a headless browser for better rotation efficiency.

How to Scrape SimilarWeb Website Analytics?

The SimilarWeb website analytics pages is a powerful feature that includes comprehensive insights about the domain, including:

  • Ranking: The domain's category, country, and global rank.
  • Traffic: Engagement analysis including total visits, bounce rate, and visit duration.
  • Geography: The domain's traffic by top countries.
  • Demographics: The visitors' composition distribution by age and gender.
  • Interests: The visitors' interests by categories and topics.
  • Competitors: The domain's competitors and alternatives and their similarities.
  • Traffic sources: The domain's traffic by its source, such as search, direct, or emails.
  • Keywords: Top keywords visitors use to search the domain.

First, let's look at what the website analysis page on our target website looks like by targeting a specific domain: Google.com. Go to the domain page SimilarWeb, and you will get a page similar to this:

How to Scrape SimilarWeb Website Traffic Analytics
Google analytics page on SimilarWeb

The above page data are challenging to scrape using selectors, as they are mostly located in charts and graphs. Therefore, we'll use the hidden web data approach.

Search through the HTML using the following XPath selector:

//script[contains(text(), 'window. __APP_DATA__')]. The script tag found contains a comprehensive JSON dataset with the domain analysis data:

How to Scrape SimilarWeb Website Traffic Analytics

To scrape SimilarWeb traffic analytics pages, we'll select this script tag and parse the inside JOSN data.

Python:


python
import re
import asyncio
import json
from typing import List, Dict
from httpx import AsyncClient, Response
from parsel import Selector
from loguru import logger as log

# initialize an async httpx client
client = AsyncClient(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
        "Cookie": "_abck=D2F915DBAC628EA7C01A23D7AA5DF495~0~YAAQLvR6XFLvH1uOAQAAJcI+ZgtcRlotheILrapRd0arqRZwbP71KUNMK6iefMI++unozW0X7uJgFea3Mf8UpSnjpJInm2rq0py0kfC+q1GLY+nKzeWBFDD7Td11X75fPFdC33UV8JHNmS+ET0pODvTs/lDzog84RKY65BBrMI5rpnImb+GIdpddmBYnw1ZMBOHdn7o1bBSQONMFqJXfIbXXEfhgkOO9c+DIRuiiiJ+y24ubNN0IhWu7XTrcJ6MrD4EPmeX6mFWUKoe/XLiLf1Hw71iP+e0+pUOCbQq1HXwV4uyYOeiawtCcsedRYDcyBM22ixz/6VYC8W5lSVPAve9dabqVQv6cqNBaaCM2unTt5Vy+xY3TCt1s8a0srhH6qdAFdCf9m7xRuRsi6OarPvDYjyp94oDlKc0SowI=~-1~-1~-1"
    },
)

def parse_hidden_data(response: Response) -> List[Dict]:
    """parse website insights from hidden script tags"""
    selector = Selector(response.text)
    script = selector.xpath("//script[contains(text(), 'window. __APP_DATA__')]/text()").get()
    data = json.loads(re.findall(r"(\{.*?)(?=window\. __APP_META__ )", script, re.DOTALL)[0])
    return data

async def scrape_website(domains: List[str]) -> List[Dict]:
    """scrape website inights from website pages"""
    # define a list of similarweb URLs for website pages
    urls = [f"https://www.similarweb.com/website/{domain}/" for domain in domains]
    to_scrape = [client.get(url) for url in urls]
    data = []
    for response in asyncio.as_completed(to_scrape):
        response = await response
        website_data = parse_hidden_data(response)["layout"]["data"]
        data.append(website_data)
    log.success(f"scraped {len(data)} website insights from similarweb website pages")
    return data
Enter fullscreen mode Exit fullscreen mode

ScrapFly:


python
import re
import asyncio
import json
from typing import List, Dict
from loguru import logger as log
from scrapfly import ScrapeConfig, ScrapflyClient, ScrapeApiResponse

SCRAPFLY = ScrapflyClient(key="Your ScrapFly API key")

def parse_hidden_data(response: ScrapeApiResponse) -> List[Dict]:
    """parse website insights from hidden script tags"""
    selector = response.selector
    script = selector.xpath("//script[contains(text(), 'window. __APP_DATA__')]/text()").get()
    data = json.loads(re.findall(r"(\{.*?)(?=window\. __APP_META__ )", script, re.DOTALL)[0])
    return data

async def scrape_website(domains: List[str]) -> List[Dict]:
    """scrape website inights from website pages"""
    # define a list of similarweb URLs for website pages
    urls = [f"https://www.similarweb.com/website/{domain}/" for domain in domains]
    to_scrape = [ScrapeConfig(url, asp=True, country="US") for url in urls]
    data = []
    async for response in SCRAPFLY.concurrent_scrape(to_scrape):
        website_data = parse_hidden_data(response)["layout"]["data"]
        data.append(website_data)
    log.success(f"scraped {len(data)} website insights from similarweb website pages")
    return data
Enter fullscreen mode Exit fullscreen mode

Run the code:


python
async def run():
    data = await scrape_website(
        domains=["google.com", "twitter.com", "instagram.com"]
    )
    # save the data to a JSON file
    with open("websites.json", "w", encoding="utf-8") as file:
        json.dump(data, file, indent=2, ensure_ascii=False)

if __name__ == " __main__":
    asyncio.run(run())
Enter fullscreen mode Exit fullscreen mode

🤖 Update the \_abck cookie before running the above code, as it may expire, to avoid challenge validation blocking or use the ScrapFly code tab instead.

Let's break down the above SimilarWeb scraping code:

  • parse_hidden_data: For selecting the script tag that contains the domain analysis data and then parsing the JSON data using regex to execute the HTML tags.
  • scrape_website: For creating the domain analytics page URLs on SimilarWeb and then requesting them concurrently while utilizing the parsing logic.

Here's an example output of the results we got:

Example output:


json
[
  {
    "interests": {
      "interestedWebsitesTotalCount": 10,
      "topInterestedWebsites": [
        {
          "domain": "facebook.com",
          "icon": "https://site-images.similarcdn.com/image?url=facebook.com&t=2&s=1&h=be773d6b77aa3d59b6a671c5c27ad729b1ae77400e89776e2f749cce6b926c4b"
        },
        ....
      ],
      "topInterestedTopics": [
        "news",
        "software",
        "online",
        "games",
        "porn"
      ],
      "topInterestedCategories": [
        "games/video_games_consoles_and_accessories",
        "adult",
        "computers_electronics_and_technology/computers_electronics_and_technology",
        "computers_electronics_and_technology/programming_and_developer_software",
        "news_and_media"
      ]
    },
    "competitors": {
      "topSimilarityCompetitors": [
        {
          "domain": "twitter.com",
          "icon": "https://site-images.similarcdn.com/image?url=twitter.com&t=2&s=1&h=05438debe431144d9c727828570d1754a25bd9286bc14f3aa65a4f05b9057e25",
          "visitsTotalCount": 5761605539,
          "categoryId": "computers_electronics_and_technology/social_networks_and_online_communities",
          "categoryRank": 3,
          "affinity": 1,
          "isDataFromGa": false
        },
        ....
      ]
    },
    "searchesSource": {
      "organicSearchShare": 0.9975672362655021,
      "paidSearchShare": 0.002432763734497856,
      "keywordsTotalCount": 17947,
      "topKeywords": [
        {
          "name": "instagram",
          "estimatedValue": 32674904.69996643,
          "volume": 101034090,
          "cpc": 0.204557390625
        },
        ....
      ]
    },
    "incomingReferrals": {
      "referralSitesTotalCount": 915,
      "topReferralSites": [
        {
          "domain": "",
          "icon": "",
          "visitsShare": 0.12224650345933631,
          "isLocked": true,
          "isAvailable": true
        },
        ....
      ],
      "topIncomingCategories": [
        {
          "category": "News_and_Media",
          "visitsShare": 0.15784273881871516
        },
        ....
      ]
    },
    "adsSource": {
      "adsSitesTotalCount": 455,
      "adsNetworksTotalCount": 67,
      "topAdsSites": [
        {
          "domain": "",
          "icon": "",
          "visitsShare": 0.1853011237551163,
          "isLocked": true,
          "isAvailable": true
        },
        ....
      ]
    },
    "socialNetworksSource": {
      "topSocialNetworks": [
        {
          "name": "Facebook",
          "visitsShare": 0.43057689186747783,
          "icon": "https://site-images.similarcdn.com/image?url=facebook.com&t=2&s=1&h=be773d6b77aa3d59b6a671c5c27ad729b1ae77400e89776e2f749cce6b926c4b"
        },
        ....
      ],
      "socialNetworksTotalCount": 79
    },
    "outgoingReferrals": {
      "outgoingSitesTotalCount": 0,
      "topOutgoingSites": [],
      "topOutgoingCategories": []
    },
    "compareCompetitor": null,
    "technologies": {
      "categories": [
        {
          "categoryId": "advertising",
          "topTechName": "PubMatic",
          "topTechIconUrl": "https://s3.amazonaws.com/s3-static-us-east-1.similarweb.com/technographics/id=331",
          "technologiesTotalCount": 4
        },
        ....
      ],
      "categoriesTotalCount": 9,
      "technologiesTotalCount": 21
    },
    "recentAds": {
      "recentAds": [
        {
          "creativeId": "a30a51acfa0ff47a40c41c4fe0ef4fd05d00_10d040f2",
          "preview": "https://sw-df-ads-scraping-creatives-production.s3.amazonaws.com/creatives/a30a51acfa0ff47a40c41c4fe0ef4fd05d00_10d040f2.jpeg?AWSAccessKeyId=AKIAIIYZKCNDR6FJZFPQ&Expires=1711717983&Signature=FgE0EitrZtikuKOvpLIdENTpxVU%3D",
          "height": 90,
          "width": 970,
          "activeDays": 1311
        },
        ....
      ],
      "isMoreAds": true
    },
    "snapshotDate": "2024-02-01T00:00:00+00:00",
    "domain": "instagram.com",
    "icon": "https://site-images.similarcdn.com/image?url=instagram.com&t=2&s=1&h=acbe9ff09f263f0114ce8473b3d3e401bfdc360d5aff845e04182e8d2335ba49",
    "previewDesktop": "https://site-images.similarcdn.com/image?url=instagram.com&t=1&s=1&h=acbe9ff09f263f0114ce8473b3d3e401bfdc360d5aff845e04182e8d2335ba49",
    "previewMobile": "https://site-images.similarcdn.com/image?url=instagram.com&t=4&s=1&h=acbe9ff09f263f0114ce8473b3d3e401bfdc360d5aff845e04182e8d2335ba49",
    "isInvalidTrafficData": false,
    "domainGaStatus": 0,
    "isDataFromGaHighlyDiscrepant": false,
    "isDataFromGa": false,
    "categoryId": "computers_electronics_and_technology/social_networks_and_online_communities",
    "overview": {
      "description": "create an account or log in to instagram - a simple, fun & creative way to capture, edit & share photos, videos & messages with friends & family.",
      "globalRank": 4,
      "globalRankChange": 0,
      "countryAlpha2Code": "US",
      "countryUrlCode": "united-states",
      "countryRank": 5,
      "countryRankChange": 1,
      "categoryRank": 2,
      "categoryRankChange": 0,
      "visitsTotalCount": 6559108584,
      "bounceRate": 0.35884756897538095,
      "pagesPerVisit": 11.602903725123301,
      "visitsAvgDurationFormatted": "00:08:22",
      "companyFeedbackRecaptcha": "6LfEq1gUAAAAACEE4w7Zek8GEmBooXMMWDpBjI6r",
      "companyName": "Instagram, Inc.",
      "companyYearFounded": 2010,
      "companyHeadquarterCountryCode": "US",
      "companyHeadquarterStateCode": 8406,
      "companyHeadquarterCity": "Menlo Park",
      "companyEmployeesMin": 10001,
      "companyEmployeesMax": null,
      "companyRevenueMin": 1000000000,
      "companyRevenueMax": null,
      "companyCategoryId": "computers_electronics_and_technology/social_networks_and_online_communities",
      "companyRevenueCurrency": null,
      "companyParentDomain": "instagram.com"
    },
    "traffic": {
      "visitsTotalCount": 6559108584,
      "visitsTotalCountChange": -0.06445071465341932,
      "bounceRate": 0.35884756897538095,
      "pagesPerVisit": 11.602903725123301,
      "visitsAvgDurationFormatted": "00:08:22",
      "history": [
        {
          "date": "2023-12-01T00:00:00",
          "visits": 6877387705
        },
        ....
      ],
      "competitors": [
        {
          "domain": "instagram.com",
          "icon": "https://site-images.similarcdn.com/image?url=instagram.com&t=2&s=1&h=acbe9ff09f263f0114ce8473b3d3e401bfdc360d5aff845e04182e8d2335ba49",
          "isDataFromGa": false,
          "visits": 6559108584
        },
        ....
      ]
    },
    "trafficSources": {
      "directVisitsShare": 0.7225718475171395,
      "referralVisitsShare": 0.03671589976432921,
      "organicSearchVisitsShare": 0.1715834983688537,
      "paidSearchVisitsShare": 0.00041844007811711777,
      "socialNetworksVisitsShare": 0.0641981602879241,
      "mailVisitsShare": 0.004222807581810079,
      "adsVisitsShare": 0.0002893464018264397,
      "topCompetitorInsight": {
        "domain": "twitter.com",
        "source": "DirectVisitsShare",
        "share": 0.8029530189588602,
        "icon": "https://site-images.similarcdn.com/image?url=twitter.com&t=2&s=1&h=05438debe431144d9c727828570d1754a25bd9286bc14f3aa65a4f05b9057e25"
      }
    },
    "ranking": {
      "globalRankCompetitors": [
        {
          "rank": 2,
          "domain": "youtube.com",
          "icon": "https://site-images.similarcdn.com/image?url=youtube.com&t=2&s=1&h=e117fb09ba0a34dee9830863bf927d29fc864e342583a36a667bf12346e88e20"
        },
        ....
      ],
      "globalRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 4
        },
        ....
      ],
      "countryRankCompetitors": [
        {
          "rank": 3,
          "domain": "facebook.com",
          "icon": "https://site-images.similarcdn.com/image?url=facebook.com&t=2&s=1&h=be773d6b77aa3d59b6a671c5c27ad729b1ae77400e89776e2f749cce6b926c4b"
        },
        ....
      ],
      "countryRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 6
        },
        ....
      ],
      "categoryRankCompetitors": [
        {
          "rank": 1,
          "domain": "facebook.com",
          "icon": "https://site-images.similarcdn.com/image?url=facebook.com&t=2&s=1&h=be773d6b77aa3d59b6a671c5c27ad729b1ae77400e89776e2f749cce6b926c4b"
        },
        ....
      ],
      "categoryRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 2
        },
        ....
      ],
      "globalRank": 4,
      "globalRankPrev": 4,
      "globalRankChange": 0,
      "categoryRank": 2,
      "categoryRankPrev": 2,
      "categoryRankChange": 0,
      "countryRank": 5,
      "countryRankPrev": 6,
      "countryRankChange": 1,
      "countryAlpha2Code": "US",
      "countryUrlCode": "united-states"
    },
    "demographics": {
      "ageDistribution": [
        {
          "minAge": 25,
          "maxAge": 34,
          "value": 0.31120395140296164
        },
        ....
      ],
      "genderDistribution": {
        "male": 0.5417371572698492,
        "female": 0.45826284273015083
      }
    },
    "geography": {
      "countriesTotalCount": 161,
      "topCountriesTraffics": [
        {
          "countryAlpha2Code": "US",
          "countryUrlCode": "united-states",
          "visitsShare": 0.19436890376964308,
          "visitsShareChange": -0.061281447749603424
        },
        ....
      ]
    }
  },
  ...
]
Enter fullscreen mode Exit fullscreen mode

The above web scraping SimilarWeb results are the raw analytics data. We can use it for further analysis ourselves!

How to Scrape SimilarWeb Website Comparing Pages?

The SimilarWeb comparing pages are similar to the dedicated pages for website analytics. They include traffic insights for two compared domains.

For example, let's compare Twitter and Instagram using our target website. Go to the compare page on SimilarWeb, and you will get a similar page:

How to Scrape SimilarWeb Website Traffic Analytics
SimilarWeb compare pages

To scrape the above data, we'll use the hidden data approach again using the previously used selector //script[contains(text(), 'window. __APP_DATA__')]. The data inside the script tag looks like the following:

How to Scrape SimilarWeb Website Traffic Analytics

Similar to our previous SimilarWeb scraping code, we'll select the script tag and parse the inside data.

Python:


python
import jmespath
import re
import asyncio
import json
from typing import List, Dict, Optional
from httpx import AsyncClient, Response
from parsel import Selector
from loguru import logger as log

# initialize an async httpx client
client = AsyncClient(
    # enable http2
    http2=True,
    # add basic browser like headers to prevent getting blocked
    headers={
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
        "Cookie": "_abck=D2F915DBAC628EA7C01A23D7AA5DF495~0~YAAQLvR6XFLvH1uOAQAAJcI+ZgtcRlotheILrapRd0arqRZwbP71KUNMK6iefMI++unozW0X7uJgFea3Mf8UpSnjpJInm2rq0py0kfC+q1GLY+nKzeWBFDD7Td11X75fPFdC33UV8JHNmS+ET0pODvTs/lDzog84RKY65BBrMI5rpnImb+GIdpddmBYnw1ZMBOHdn7o1bBSQONMFqJXfIbXXEfhgkOO9c+DIRuiiiJ+y24ubNN0IhWu7XTrcJ6MrD4EPmeX6mFWUKoe/XLiLf1Hw71iP+e0+pUOCbQq1HXwV4uyYOeiawtCcsedRYDcyBM22ixz/6VYC8W5lSVPAve9dabqVQv6cqNBaaCM2unTt5Vy+xY3TCt1s8a0srhH6qdAFdCf9m7xRuRsi6OarPvDYjyp94oDlKc0SowI=~-1~-1~-1"
    },
)

def parse_hidden_data(response: Response) -> List[Dict]:
    """parse website insights from hidden script tags"""
    selector = Selector(response.text)
    script = selector.xpath("//script[contains(text(), 'window. __APP_DATA__')]/text()").get()
    data = json.loads(re.findall(r"(\{.*?)(?=window\. __APP_META__ )", script, re.DOTALL)[0])
    return data

def parse_website_compare(response: Response, first_domain: str, second_domain: str) -> Dict:
    """parse website comparings inights between two domains"""

    def parse_domain_insights(data: Dict, second_domain: Optional[bool]=None) -> Dict:
        """parse each website data and add it to each domain"""
        data_key = data["layout"]["data"]
        if second_domain:
            data_key = data_key["compareCompetitor"] # the 2nd website compare key is nested
        parsed_data = jmespath.search(
            """{
            overview: overview,
            traffic: traffic,
            trafficSources: trafficSources,
            ranking: ranking,
            demographics: geography
            }""",
            data_key
        )
        return parsed_data

    script_data = parse_hidden_data(response)
    data = {}
    data[first_domain] = parse_domain_insights(data=script_data)
    data[second_domain] = parse_domain_insights(data=script_data, second_domain=True)
    return data

async def scrape_website_compare(first_domain: str, second_domain: str) -> Dict:
    """parse website comparing data from similarweb comparing pages"""
    url = f"https://www.similarweb.com/website/{first_domain}/vs/{second_domain}/"
    response = await client.get(url)
    data = parse_website_compare(response, first_domain, second_domain)
    f"scraped comparing insights between {first_domain} and {second_domain}"
    log.success(f"scraped comparing insights between {first_domain} and {second_domain}")
    return data
Enter fullscreen mode Exit fullscreen mode

ScrapFly:


python
import jmespath
import re
import asyncio
import json
from typing import List, Dict, Optional
from loguru import logger as log
from scrapfly import ScrapeConfig, ScrapflyClient, ScrapeApiResponse

SCRAPFLY = ScrapflyClient(key="Your ScrapFly API key")

def parse_hidden_data(response: ScrapeApiResponse) -> List[Dict]:
    """parse website insights from hidden script tags"""
    selector = response.selector
    script = selector.xpath("//script[contains(text(), 'window. __APP_DATA__')]/text()").get()
    data = json.loads(re.findall(r"(\{.*?)(?=window\. __APP_META__ )", script, re.DOTALL)[0])
    return data

def parse_website_compare(response: ScrapeApiResponse, first_domain: str, second_domain: str) -> Dict:
    """parse website comparings inights between two domains"""

    def parse_domain_insights(data: Dict, second_domain: Optional[bool]=None) -> Dict:
        """parse each website data and add it to each domain"""
        data_key = data["layout"]["data"]
        if second_domain:
            data_key = data_key["compareCompetitor"] # the 2nd website compare key is nested
        parsed_data = jmespath.search(
            """{
            overview: overview,
            traffic: traffic,
            trafficSources: trafficSources,
            ranking: ranking,
            demographics: geography
            }""",
            data_key
        )
        return parsed_data

    script_data = parse_hidden_data(response)
    data = {}
    data[first_domain] = parse_domain_insights(data=script_data)
    data[second_domain] = parse_domain_insights(data=script_data, second_domain=True)
    return data

async def scrape_website_compare(first_domain: str, second_domain: str) -> Dict:
    """parse website comparing data from similarweb comparing pages"""
    url = f"https://www.similarweb.com/website/{first_domain}/vs/{second_domain}/"
    response = await SCRAPFLY.async_scrape(ScrapeConfig(url, country="US", asp=True))
    data = parse_website_compare(response, first_domain, second_domain)
    f"scraped comparing insights between {first_domain} and {second_domain}"
    log.success(f"scraped comparing insights between {first_domain} and {second_domain}")
    return data
Enter fullscreen mode Exit fullscreen mode

Run the code:


python
async def run():
    comparing_data = await scrape_website_compare(
        first_domain="twitter.com",
        second_domain="instagram.com"
    )
    # save the data to a JSON file
    with open("websites_compare.json", "w", encoding="utf-8") as file:
        json.dump(comparing_data, file, indent=2, ensure_ascii=False)

if __name__ == " __main__":
    asyncio.run(run())
Enter fullscreen mode Exit fullscreen mode

In the above code, we use the previously defined parse_hidden_data to parse data from the page and define two additional functions:

  • parse_website_compare: For organizing the JSON data and parsing it to exclude unnecessary details with JMESPath.
  • scrape_website_compare: For defining the SimilarWeb comparing URL and requesting it, while utilizing the parsing logic.

Here is a sample output of the results we got:


json
{
  "twitter.com": {
    "overview": {
      "description": "the latest stories on twitter - as told by tweets.",
      "globalRank": 5,
      "globalRankChange": 0,
      "countryAlpha2Code": "US",
      "countryUrlCode": "united-states",
      "countryRank": 7,
      "countryRankChange": 0,
      "categoryRank": 3,
      "categoryRankChange": 0,
      "visitsTotalCount": 5761605539,
      "bounceRate": 0.31973927509903083,
      "pagesPerVisit": 10.723622448514728,
      "visitsAvgDurationFormatted": "00:11:03",
      "companyFeedbackRecaptcha": "6LfEq1gUAAAAACEE4w7Zek8GEmBooXMMWDpBjI6r",
      "companyName": null,
      "companyYearFounded": null,
      "companyHeadquarterCountryCode": null,
      "companyHeadquarterStateCode": null,
      "companyHeadquarterCity": null,
      "companyEmployeesMin": null,
      "companyEmployeesMax": null,
      "companyRevenueMin": null,
      "companyRevenueMax": null,
      "companyCategoryId": "",
      "companyRevenueCurrency": null,
      "companyParentDomain": null
    },
    "traffic": {
      "visitsTotalCount": 5761605539,
      "visitsTotalCountChange": -0.08130202734065403,
      "bounceRate": 0.31973927509903083,
      "pagesPerVisit": 10.723622448514728,
      "visitsAvgDurationFormatted": "00:11:03",
      "history": [
        {
          "date": "2023-12-01T00:00:00",
          "visits": 6237810432
        },
        ....
      ],
      "competitors": [
        {
          "domain": "twitter.com",
          "icon": "https://site-images.similarcdn.com/image?url=twitter.com&t=2&s=1&h=05438debe431144d9c727828570d1754a25bd9286bc14f3aa65a4f05b9057e25",
          "isDataFromGa": false,
          "visits": 5761605539
        }
      ]
    },
    "trafficSources": {
      "directVisitsShare": 0.8029530189588602,
      "referralVisitsShare": 0.04303306407258124,
      "organicSearchVisitsShare": 0.11258429980814376,
      "paidSearchVisitsShare": 2.3072165238041076e-05,
      "socialNetworksVisitsShare": 0.03595580708833726,
      "mailVisitsShare": 0.005194380408304638,
      "adsVisitsShare": 0.0002563574985346188,
      "topCompetitorInsight": {
        "domain": "",
        "source": "",
        "share": 0,
        "icon": ""
      }
    },
    "ranking": {
      "globalRankCompetitors": [],
      "globalRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 5
        },
        ....
      ],
      "countryRankCompetitors": [],
      "countryRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 7
        },
        ....
      ],
      "categoryRankCompetitors": [],
      "categoryRankHistory": [
        {
          "date": "2023-12-01T00:00:00+00:00",
          "rank": 3
        },
        ....
      ],
      "globalRank": 5,
      "globalRankPrev": 5,
      "globalRankChange": 0,
      "categoryRank": 3,
      "categoryRankPrev": 3,
      "categoryRankChange": 0,
      "countryRank": 7,
      "countryRankPrev": 7,
      "countryRankChange": 0,
      "countryAlpha2Code": "US",
      "countryUrlCode": "united-states"
    },
    "demographics": {
      "countriesTotalCount": null,
      "topCountriesTraffics": [
        {
          "countryAlpha2Code": "US",
          "countryUrlCode": "united-states",
          "visitsShare": 0.5658495543788219,
          "visitsShareChange": null
        },
        ....
      ]
    }
  },
  "instagram.com": {
    // The same previous data schema
    ....
  }
}
Enter fullscreen mode Exit fullscreen mode

For further details on JMESPath, refer to our dedicated guide.

With this last feature, our SimilarWeb scraper is complete. It can scrape tons of website traffic data from sitemaps, trending, domain, and comparing pages. However, our scraper will soon encounter a major challenge: scraping blocking!

Bypass SimilarWeb Web Scraping Blocking

We can successfully scrape SimilarWeb for a limited amount of requests. However, attempting to scale our scraper will lead SimilarWeb to block the IP address or request us to log in:

How to Scrape SimilarWeb Website Traffic Analytics
SimilarWeb scraping blocking

To scrape SimilarWeb without getting blocked, we'll use ScrapFly - a web scraping API that allows for scraping at scale by providing:

How to Scrape SimilarWeb Website Traffic Analytics
ScrapFly service does the heavy lifting for you!

To use the ScrapFly scraping API to avoid blocking, all we have to do is enable the asp parameter and select a proxy country:


python
# standard web scraping code
import httpx
from parsel import Selector

response = httpx.get("some similarweb.com URL")
selector = Selector(response.text)

# in ScrapFly becomes this 👇
from scrapfly import ScrapeConfig, ScrapflyClient

# replaces your HTTP client (httpx in this case)
scrapfly = ScrapflyClient(key="Your ScrapFly API key")

response = scrapfly.scrape(ScrapeConfig(
    url="website URL",
    asp=True, # enable the anti scraping protection to bypass blocking
    proxy_pool="public_residential_pool", # select the residential proxy pool
    country="US", # set the proxy location to a specfic country
    render_js=True # enable rendering JavaScript (like headless browsers) to scrape dynamic content if needed
))

# use the built in Parsel selector
selector = response.selector
# access the HTML content
html = response.scrape_result['content']
Enter fullscreen mode Exit fullscreen mode

Try for FREE!

FAQ

To wrap up this guide on SimilarWeb web scraping, let's have a look at some frequently asked questions.

Are there public APIs for SimilarWeb?

SimilarWeb offers a subscription-based API. However, extracting data from SimilarWeb is straightforward, and you can use it to create your own scraper API.

Are there alternatives for scraping SimilarWeb?

Yes, you can scrape Google Trends and SEO keywords for similar web traffic insights. For more website scraping tutorials, refer to our #scrapeguide blog tag.

Full SimilarWeb Scraper Code

Summary

In this guide, we explained how to scrape SimilarWeb with Python. We started by exploring and navigating the website by scraping sitemaps. Then, we went through a step-by-step guide on scraping several SimilarWeb pages for traffic, rankings, trending, and comparing data.

We have also explored bypassing web scraping SimilarWeb without getting blocked using ScrapFly and avoiding its validation challenges.

Top comments (0)

Read next

beddetail5 profile image

Understanding Tech Shifts and Its Influence on Corporate Environments

Irwin Gutierrez -

nr18 profile image

Boost Your Productivity with awscurl: Simplifying IAM-Secured API Testing in AWS

Joris Conijn -

mikeyoung44 profile image

AI and the Black Box Problem: How Machine Learning Challenges Mathematical Proof Verification

Mike Young -

mikeyoung44 profile image

LLM Test Generators Miss Critical Bugs Due to Design Flaws, Study Shows

Mike Young -