I want that they will get the data up to 8 link
because after 8 link there will be no data in the link as you show in pic after the 8 link there will be no data in it as you seen in csv file in pic so how I will do apply limit that they will get data upto 8 link
these is website link https://www.linkedin.com/learning/search?keywords=data%20science
JSON API
Code part
import requests
import pandas as pd
url = "https://www.linkedin.com/learning-api/searchV2?keywords=data%20science&q=keywords&searchRequestId=RW4AuZRJT22%2BUeXnsZJGQA%3D%3D"
payload={}
headers = {
'authority': 'www.linkedin.com',
'accept': 'application/vnd.linkedin.normalized+json+2.1',
'accept-language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'cookie': 'bscookie="v=1&202108281231498ed9b977-a15a-4647-83ff-d0ef12adfbfbAQFdf9p_GSaBPrFkmyztJ8zyOnqVND-D"; li_theme=light; li_theme_set=app; li_sugr=4752e3dd-9232-4bb9-9dbb-b29c1a127f77; bcookie="v=2&9fb3a4d0-1139-4e2b-89ba-e5374eeb9735"; aam_uuid=08800810176251362264578372297522883472; _gcl_au=1.1.240501668.1664707206; li_rm=AQELLfU3ZqmMhAAAAYQ_tPjGK8ONpN3EEUxH1P4M6Czq5fk6EXaEXSzKwoNSXoSZ7KgO5uSTE9iZ30fuhs6ju1rLH1VgXYyRM3nNuiTQEx1k2ca6SR0Hk1d5-NBafeE0zv65QetFY5Yrx2ufzRlfEXUkJJSoO9Z2o7MeuX-3Go7P4dI-m5HQM7VOKLiK_TD-ZWzj_OkdkR75K31QKGq8bxPLa0JpkGUzhDIVGWzl6vqkcl6BJEK2s-keIZjsiH5MZ9sbLXEVOxLg4vD21TTJBNshE6zaiWrSnxx_PEm44eDPqjvXRMVWFeX7VZfIe2KFshWXLRc4SY8hAQINymU; visit=v=1&M; G_ENABLED_IDPS=google; JSESSIONID="ajax:7673827752327651374"; timezone=Asia/Karachi; _guid=0f0d3402-80be-4bef-9baf-18d281f68921; mbox=session^#965dfb20b29e4f2688eedcf643d2e5ab^#1671620169|PC^#965dfb20b29e4f2688eedcf643d2e5ab.38_0^#1687170309; __ssid=db28305b-28da-4f8b-ad3a-54dea10b9eb9; dfpfpt=da2e5dde482a41b09cf7178ba1bcec7e; g_state={"i_l":0}; liap=true; li_at=AQEDATKxuC8DTVh9AAABhaytidQAAAGGZN5q6E0AdHv14xrDnsngkfFuMyIIbGYccHR15UrPQ8rb3qpS0_-mpCFm9pXQkoNYGdk87LiGVIqiw4oXuJ9tqflCEOev71_L83JoJ-fkbOfZwdG0RICtuIHn; AnalyticsSyncHistory=AQKUIualgILMBgAAAYZHP2t3mvejt25dMqUMRmrpyhaQMe1cucNiAMliFNRUf4cu4aKnZ1z1kQ_FGeqFr2m04Q; lms_ads=AQEr9ksNAL4kugAAAYZHP2z8QK26stPkoXe2TgJZW3Fnrl4dCzbC2DtithS1-zp5Ve85QwxzRhPvP9okaC0kbu40FYX7EqIk; lms_analytics=AQEr9ksNAL4kugAAAYZHP2z8QK26stPkoXe2TgJZW3Fnrl4dCzbC2DtithS1-zp5Ve85QwxzRhPvP9okaC0kbu40FYX7EqIk; fid=AQGWcXnO5AffyAAAAYZRr6tph6cekZ9ZD66e1xdHhumlVvJ3cKYzZLwfK-I3nJyeRyLQs3LRnowKjQ; lil-lang=en_US; lang=v=2&lang=en-us; _dd_l=1; _dd=ff90da3c-aa07-4491-9106-b226eba1c09c; AMCVS_14215E3D5995C57C0A495C55%40AdobeOrg=1; AMCV_14215E3D5995C57C0A495C55%40AdobeOrg=-637568504%7CMCIDTS%7C19403%7CMCMID%7C09349215808923073694559483836331055195%7CMCAAMLH-1677084815%7C3%7CMCAAMB-1677084815%7CRKhpRz8krg2tLO6pguXWp5olkAcUniQYPHaMWWgdJ3xzPWQmdj0y%7CMCOPTOUT-1676487215s%7CNONE%7CMCCIDH%7C1076847823%7CvVersion%7C5.1.1; s_cc=true; UserMatchHistory=AQJJ3j-efkcQeQAAAYZWAETxBE44VVBGzo_i-gr5nEGPOK85mS3kDScLdGC24_GeNx-GEeCNDrPOjkQde_MGT4iPc7vJV4sT_nPL8Tv4WMTLarIEliLYPkCvou8zFlb3dFNkbXZjVV_KTVeDvUSJ5WJTeStLNXmzV3_EV5mI9dbSRpoTFlJ94vi_zxcCmnLTaGAYGQAdymMv4SbaMgtnt3QcY8Zj9-hnwxdsIEmJloq47_QTP7sfl-SG-vw8xvhl9KYb0ZPKCnQ6ioJhu3G4cFpKJiSUbULkYMADSo0; lidc="b=VB23:s=V:r=V:a=V:p=V:g=4060:u=105:x=1:i=1676480108:t=1676566269:v=2:sig=AQEz2UktgVcQuJwMoVRgKgnUuKtCEm9C"; s_sq=%5B%5BB%5D%5D; gpv_pn=www.linkedin.com%2Flearning%2Fsearch; s_ips=615; s_plt=7.03; s_pltp=www.linkedin.com%2Flearning%2Fsearch; s_tp=6116; s_ppv=www.linkedin.com%2Flearning%2Fsearch%2C47%2C10%2C2859%2C7%2C18; s_tslv=1676480356388',
'csrf-token': 'ajax:7673827752327651374',
'referer': 'https://www.linkedin.com/learning/search?keywords=data%20science',
'sec-ch-ua': '"Chromium";v="110", "Not A(Brand";v="24", "Google Chrome";v="110"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36',
'x-li-lang': 'en_US',
'x-li-page-instance': 'urn:li:page:d_learning_search;gNOg2MJoSqWv2XNAh4ukiQ==',
'x-li-pem-metadata': 'Learning Exp - Search=search',
'x-li-track': '{"clientVersion":"1.1.2236","mpVersion":"1.1.2236","osName":"web","timezoneOffset":5,"timezone":"Asia/Karachi","mpName":"learning-web","displayDensity":1,"displayWidth":1366,"displayHeight":768}',
'x-lil-intl-library': 'en_US',
'x-restli-protocol-version': '2.0.0'
}
res = requests.request("GET", url, headers=headers, data=payload).json()
product=[]
items=res['included']
for item in items:
try:
title=item['headline']['title']['text']
except:
title=''
try:
url='https://www.linkedin.com/learning/'+item['slug']
except:
url=''
try:
rating=item['rating']['ratingCount']
except:
rating=''
wev={
'title':title,
'instructor':name,
'review':rating,
'url':url
}
product.append(wev)
df=pd.DataFrame(product)
df.to_csv('learning.csv')
source https://stackoverflow.com/questions/75463567/scraping-data-through-api-from-json
Comments
Post a Comment