Вы можете использовать пакет google-search-results для извлечения данных из Академии Google. Он использует SerpApi - платный API с бесплатной пробной версией.
Полный пример
from serpapi import GoogleSearch
import os
params = {
"engine": "google_scholar",
"q": "coffee",
"api_key": os.getenv("API_KEY")
}
client = GoogleSearch(params)
data = client.get_dict()
print("Organic results\n")
for result in data['organic_results']:
print(f"""Title: {result['title']}
Result ID: {result['result_id']}
Link: {result['link']}
Snippet: {result['snippet']}
""")
if 'resources' in result:
print(f"Resource: {result['resources'][0]}")
Ответ
{
"organic_results": [
{
"position": 0,
"title": "Phenolic compounds in coffee",
"result_id": "re9ssrU-exUJ",
"type": "Html",
"link": "http://www.scielo.br/scielo.php?pid=S1677-04202006000100003&script=sci_arttext",
"snippet": "Phenolic compounds are secondary metabolites generally involved in plant adaptation to environmental stress conditions. Chlorogenic acids (CGA) and related compounds are the main components of the phenolic fraction of green coffee beans, reaching levels up to …",
"publication_info": {
"summary": "A Farah, CM Donangelo - Brazilian journal of plant physiology, 2006 - SciELO Brasil"
},
"resources": [
{
"title": "scielo.br",
"file_format": "HTML",
"link": "http://www.scielo.br/scielo.php?pid=S1677-04202006000100003&script=sci_arttext"
}
],
"inline_links": {
"serpapi_cite_link": "https://serpapi.com/search.json?engine=google_scholar_cite&q=re9ssrU-exUJ",
"html_version": "https://scholar.google.comhttp://www.scielo.br/scielo.php?pid=S1677-04202006000100003&script=sci_arttext",
"cited_by": {
"total": 608,
"link": "https://scholar.google.com/scholar?cites=1547899847035383725&as_sdt=5,44&sciodt=0,44&hl=en",
"serpapi_scholar_link": "https://serpapi.com/search.json?cites=1547899847035383725&engine=google_scholar&hl=en&q=Coffee"
},
"related_pages_link": "https://scholar.google.com/scholar?q=related:re9ssrU-exUJ:scholar.google.com/&scioq=Coffee&hl=en&as_sdt=0,44",
"versions": {
"total": 6,
"link": "https://scholar.google.com/scholar?cluster=1547899847035383725&hl=en&as_sdt=0,44",
"serpapi_scholar_link": "https://serpapi.com/search.json?cluster=1547899847035383725&engine=google_scholar&hl=en&q=Coffee"
},
"cached_page_link": "https://scholar.google.comhttp://scholar.googleusercontent.com/scholar?q=cache:re9ssrU-exUJ:scholar.google.com/+Coffee&hl=en&as_sdt=0,44"
}
},
{
"position": 1,
"title": "Functional properties of coffee and coffee by-products",
"result_id": "9WouRiFbIK4J",
"link": "https://www.sciencedirect.com/science/article/pii/S0963996911003449",
"snippet": "Coffee, one of the most popular beverages, is consumed by millions of people every day. Traditionally, coffee beneficial effects have been attributed solely to its most intriguing and investigated ingredient, caffeine, but it is now known that other compounds also contribute to …",
"publication_info": {
"summary": "P Esquivel, VM Jiménez - Food Research International, 2012 - Elsevier",
"authors": [
{
"name": "P Esquivel",
"link": "https://scholar.google.com/citations?user=EpwJXskAAAAJ&hl=en&oi=sra"
},
{
"name": "VM Jiménez",
"link": "https://scholar.google.com/citations?user=_P0h0B8AAAAJ&hl=en&oi=sra"
}
]
},
"resources": [
{
"title": "uoregon.edu",
"file_format": "PDF",
"link": "https://pages.uoregon.edu/chendon/coffee_literature/2012%20Food%20Res.%20Int.,%20Uses%20for%20coffee%20waste.pdf"
}
],
"inline_links": {
"serpapi_cite_link": "https://serpapi.com/search.json?engine=google_scholar_cite&q=9WouRiFbIK4J",
"cited_by": {
"total": 531,
"link": "https://scholar.google.com/scholar?cites=12547128760323697397&as_sdt=5,44&sciodt=0,44&hl=en",
"serpapi_scholar_link": "https://serpapi.com/search.json?cites=12547128760323697397&engine=google_scholar&hl=en&q=Coffee"
},
"related_pages_link": "https://scholar.google.com/scholar?q=related:9WouRiFbIK4J:scholar.google.com/&scioq=Coffee&hl=en&as_sdt=0,44",
"versions": {
"total": 9,
"link": "https://scholar.google.com/scholar?cluster=12547128760323697397&hl=en&as_sdt=0,44",
"serpapi_scholar_link": "https://serpapi.com/search.json?cluster=12547128760323697397&engine=google_scholar&hl=en&q=Coffee"
}
}
},
{
"position": 2,
"title": "Coffee constituents",
"result_id": "xY3q9qnkN54J",
"link": "https://books.google.com/books?hl=en&lr=&id=y0qA89vCr3MC&oi=fnd&pg=PT47&dq=Coffee&ots=pyKSUohpI7&sig=8qULQFDS2RydGAkXlRyVJoph4AU",
"snippet": "Coffee has been for decades the most commercialized food product and most widely consumed beverage in the world. Since the opening of the first coffee house in Mecca at the end of the fifteenth century, coffee consumption has greatly increased all around the world …",
"publication_info": {
"summary": "A Farah - Coffee: Emerging health effects and disease …, 2012 - books.google.com"
},
"resources": [
{
"title": "academia.edu",
"file_format": "PDF",
"link": "http://www.academia.edu/download/52419982/IFTPressBook_Coffee_PreviewChapter.pdf"
}
],
"inline_links": {
"serpapi_cite_link": "https://serpapi.com/search.json?engine=google_scholar_cite&q=xY3q9qnkN54J",
"cited_by": {
"total": 255,
"link": "https://scholar.google.com/scholar?cites=11400832400354872773&as_sdt=5,44&sciodt=0,44&hl=en",
"serpapi_scholar_link": "https://serpapi.com/search.json?cites=11400832400354872773&engine=google_scholar&hl=en&q=Coffee"
},
"related_pages_link": "https://scholar.google.com/scholar?q=related:xY3q9qnkN54J:scholar.google.com/&scioq=Coffee&hl=en&as_sdt=0,44",
"versions": {
"total": 7,
"link": "https://scholar.google.com/scholar?cluster=11400832400354872773&hl=en&as_sdt=0,44",
"serpapi_scholar_link": "https://serpapi.com/search.json?cluster=11400832400354872773&engine=google_scholar&hl=en&q=Coffee"
}
}
}
]
}
Выход
Organic results
Title: Phenolic compounds in coffee
Result ID: re9ssrU-exUJ
Link: http://www.scielo.br/scielo.php?pid=S1677-04202006000100003&script=sci_arttext
Title: Functional properties of coffee and coffee by-products
Result ID: 9WouRiFbIK4J
Link: https://www.sciencedirect.com/science/article/pii/S0963996911003449
Title: Coffee constituents
Result ID: xY3q9qnkN54J
Link: https://books.google.com/books?hl=en&lr=&id=y0qA89vCr3MC&oi=fnd&pg=PT47&dq=coffee&ots=pyKSUokkMc&sig=sjDv_w50O-5_svJDJKPJ7hHJtRg
Title: All about coffee
Result ID: fGeQlvu-2_IJ
Link: https://books.google.com/books?hl=en&lr=&id=oJxpQX4ko7cC&oi=fnd&pg=PT1&dq=coffee&ots=Oih_E-45Y-&sig=KYyBOoSXwRdwOv5upyWwl0FzIq8
Title: Biotechnological potential of coffee pulp and coffee husk for bioprocesses
Result ID: Zu7aKNjvAUwJ
Link: https://www.sciencedirect.com/science/article/pii/S1369703X0000084X
Title: Biodiversity conservation in traditional coffee systems of Mexico
Result ID: pIjQPO7__AYJ
Link: https://conbio.onlinelibrary.wiley.com/doi/abs/10.1046/j.1523-1739.1999.97153.x
Title: Coffee flavor chemistry
Result ID: UwtLySK5iawJ
Link: https://books.google.com/books?hl=en&lr=&id=NQi1LYJxFvUC&oi=fnd&pg=PP13&dq=coffee&ots=dRSace3WYu&sig=5jyqtvqkL_jGDkWTLsLqksKiQUw
Title: Coffee and health: a review of recent human research
Result ID: fSVlrXX7dIUJ
Link: https://www.tandfonline.com/doi/abs/10.1080/10408390500400009
Title: M-Coffee: combining multiple sequence alignment methods with T-Coffee
Result ID: _3o-xhuGyg0J
Link: https://academic.oup.com/nar/article-abstract/34/6/1692/2401531
Title: Producing decaffeinated coffee plants
Result ID: VJySkcFsQ1EJ
Link: https://www.nature.com/articles/423823a
Если вам нужна дополнительная информация, ознакомьтесь с документацией по SerpApi или живая игровая площадка.
Уведомление: я работаю в SerpApi.
person
Ilya Zub
schedule
01.04.2020
