Last active
May 20, 2021 09:43
-
-
Save dimitryzub/6c73d66e85b4853b500adef553621500 to your computer and use it in GitHub Desktop.
Scrape Google Scholar Organic Results with SerpApi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from serpapi import GoogleSearch | |
import os, json | |
params = { | |
"api_key": os.getenv("API_KEY"), | |
"engine": "google_scholar", | |
"q": "samsung", | |
} | |
search = GoogleSearch(params) | |
results = search.get_dict() | |
# This print() looks pretty akward, | |
# but the point is that you can grab everything you need in 2-3 lines of code as below. | |
for result in results['organic_results']: | |
print(f"Title: {result['title']}\nPublication info: {result['publication_info']['summary']}\nSnippet: {result['snippet']}\nCited by: {result['inline_links']['cited_by']['link']}\nRelated Versions: {result['inline_links']['related_pages_link']}\n") | |
# If you want more readable code, here's one example. | |
data = [] | |
for result in results['organic_results']: | |
data.append({ | |
'title': result['title'], | |
'publication_info': result['publication_info']['summary'], | |
'snippet': result['snippet'], | |
'cited_by': result['inline_links']['cited_by']['link'], | |
'related_versions': result['inline_links']['related_pages_link'], | |
}) | |
print(json.dumps(data, indent = 2, ensure_ascii = False)) | |
# Part of Non-JSON output: | |
''' | |
Title: “What? I thought Samsung was Japanese”: accurate or not, perceived country of origin matters | |
Publication info: P Magnusson, SA Westjohn… - International Marketing …, 2011 - emerald.com | |
Snippet: Purpose–Extensive research has shown that country‐of‐origin (COO) information significantly affects product evaluations and buying behavior. Yet recently, a competing perspective has emerged suggesting that COO effects have been inflated in prior research … | |
Cited by: https://scholar.google.com/scholar?cites=341074171610121811&as_sdt=5,44&sciodt=0,44&hl=en | |
Related Versions: https://scholar.google.com/scholar?q=related:U8bh6Ca9uwQJ:scholar.google.com/&scioq=samsung&hl=en&as_sdt=0,44 | |
''' | |
# Part of JSON output: | |
''' | |
[ | |
{ | |
"title": "“What? I thought Samsung was Japanese”: accurate or not, perceived country of origin matters", | |
"publication_info": "P Magnusson, SA Westjohn… - International Marketing …, 2011 - emerald.com", | |
"snippet": "Purpose–Extensive research has shown that country‐of‐origin (COO) information significantly affects product evaluations and buying behavior. Yet recently, a competing perspective has emerged suggesting that COO effects have been inflated in prior research …", | |
"cited_by": "https://scholar.google.com/scholar?cites=341074171610121811&as_sdt=5,44&sciodt=0,44&hl=en", | |
"related_versions": "https://scholar.google.com/scholar?q=related:U8bh6Ca9uwQJ:scholar.google.com/&scioq=samsung&hl=en&as_sdt=0,44" | |
} | |
] | |
''' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment