I have a text string/script which I took out from a webpage. I would like to clean/structure that text string/Script so that I can only get JSON out of it. But its very long that I lost finding beginning and ending of JSON from that text. Does anyone help me out or advice a online website which can help to find the beginning and ending of JSON from that text. Many Thanks
window.__NUXT__=function(e,l,a,t,r,s,i,o,n,d){return{layout:s,data:[{product:{active_gtin:"5711555000616",active_supplier:"0000009002",active_supplier_product_id:"000000000091052931-EA",brand:"Prosonic",description:"Prosonic 32\" TV med Android og Full-HD opløsning. Android styresystemet giver dig let adgang til Netflix, Viaplay og TV2 Play samt mange andre apps og med indbygget Chromecast kan du let caste indhold til TV'et.",display_list_price:l,display_sales_price:l,energy_class:"A+",energy_class_color_code:"lev_3",energy_label:i,erp_product_id:o,gallery_images:[i,"https://sg-dam.imgix.net/services/assets.img/id/13a13e85-efe7-48eb-bb6c-953abc94fb08/size/original","https://sg-dam.imgix.net/services/assets.img/id/e0c39be1-eb82-4652-88f4-992226390a3f/size/original","https://sg-dam.imgix.net/services/assets.img/id/9bc81449-64ba-44c0-b691-31b22bf5dc91/size/original"],hybris_code:n,id:n,image_primary:"https://sg-dam.imgix.net/services/assets.img/id/f8d59494-3da7-4cb7-9dd8-e8d16577e7c4/size/original",in_stock_stores_count:15,is_approved_for_sale:t,is_exposed:t,is_reservable:t,name:'Prosonic 32" 32and6021 LED tv',online_from:16000344e5,online_to:2534022108e5,primary_category_path:"/elektronik/tv",product_url:"/produkter/prosonic-32-32and6021-led-tv/100553115/",sales_price:e,show_discount_message:a,sku:o,specifications:'[{"features":[{"code":"text-TvMemory","label":"Tekst TV hukommelse","value":"1000"}],"label":"Tekst TV hukommelse"},{"features":[{"code":"tvFeatures","label":"TV funktioner","value":"Netflix"},{"code":"tvFeatures","label":"TV funktioner","value":"SmartTV"},{"code":"tvFeatures","label":"TV funktioner","value":"Wi-Fi indbygget"}],"label":"TV funktioner"},{"features":[{"code":"TV.tvApps","label":"TV Apps","value":"Amazon"},{"code":"TV.tvApps","label":"TV Apps","value":"Apple TV"},{"code":"TV.tvApps","label":"TV Apps","value":"Blockbuster"},{"code":"TV.tvApps","label":"TV Apps","value":"Boxer"},{"code":"TV.tvApps","label":"TV Apps","value":"Dplay"},{"code":"TV.tvApps","label":"TV Apps","value":"DR TV"},{"code":"TV.tvApps","label":"TV Apps","value":"Google Play Store"},{"code":"TV.tvApps","label":"TV Apps","value":"HBO Nordic"},{"code":"TV.tvApps","label":"TV Apps","value":"Min Bio"},{"code":"TV.tvApps","label":"TV Apps","value":"Netflix"},{"code":"TV.tvApps","label":"TV Apps","value":"Rakuten TV"},{"code":"TV.tvApps","label":"TV Apps","value":"SF Anytime"},{"code":"TV.tvApps","label":"TV Apps","value":"Skype"},{"code":"TV.tvApps","label":"TV Apps","value":"Spotify"},{"code":"TV.tvApps","label":"TV Apps","value":"TV2 play"},{"code":"TV.tvApps","label":"TV Apps","value":"Viaplay"},{"code":"TV.tvApps","label":"TV Apps","value":"YouSee"},{"code":"TV.tvApps","label":"TV Apps","value":"Youtube"}],"label":"TV Apps"},{"features":[{"code":"connectivity.videoConnectivity","label":"Video tilslutning","value":"composite"}],"label":"Video tilslutning"},{"features":[{"code":"screen.monitorLanguageList","label":"Skærmsprog","value":"Dansk"}],"label":"Skærmsprog"},{"features":[{"code":"builtInSpeakers.soundFunction","label":"Lydfunktioner","value":"Bluetooth"}],"label":"Lydfunktioner"},{"features":[{"code":"productionYear","label":"Produktionsår","value":"2.020"}],"label":"Produktionsår"},{"features":[{"code":"electronics.manufacturerNum","label":"Producentens Varenummer","value":"32AND6021"}],"label":"Producentens Varenummer"},{"features":[{"code":"TV.hdrLOV","label":"HDR","value":"HDR 10"}],"label":"HDR"},{"features":[{"code":"TV.isSleepTimerPresent","label":"Sleep timer","value":"Ja"}],"label":"Sleep timer"},{"features":[{"code":"isPVRFunctionPresent","label":"PVR funktion","value":"Ja"}],"label":"PVR funktion"},{"features":[{"code":"accessoriesIncluded","label":"Tilbehør inkluderet","value":"stand og remote"}],"label":"Tilbehør inkluderet"},{"features":[{"code":"screenTechnologyDesc","label":"Skærmteknologi","value":"LED"}],"label":"Skærmteknologi"},{"features":[{"code":"tvTunerList","label":"TV-tuners","value":"CI+"},{"code":"tvTunerList","label":"TV-tuners","value":"DVB-C"},{"code":"tvTunerList","label":"TV-tuners","value":"DVB-S"},{"code":"tvTunerList","label":"TV-tuners","value":"DVB-T2"},{"code":"tvTunerList","label":"TV-tuners","value":"MPEG4 tuner"}],"label":"TV-tuners"},{"features":[{"code":"TV.vesaStandardList","label":"Vægbeslag Vesa standard","value":"75x75"}],"label":"Vægbeslag Vesa standard"},{"features":[{"code":"connectivity.hdmiCount","label":"Antal HDMI","value":"3"}],"label":"Antal HDMI"},{"features":[{"code":"builtInSpeakers.speakerEffect","label":"Højtalereffekt","value":"12"}],"label":"Højtalereffekt"},{"features":[{"code":"usbCount","label":"Antal USB stik","value":"1"}],"label":"Antal USB stik"},{"features":[{"code":"TVResolution","label":"TV opløsning","value":"Full HD"}],"label":"TV opløsning"},{"features":[{"code":"picturePlayers.supportedImageFormats","label":"Understøttede Billed Formater","value":"JPG,BMP,PNG,GIF"}],"label":"Understøttede Billed Formater"},{"features":[{"code":"scartCount","label":"Antal scartstik","value":"0"}],"label":"Antal scartstik"},{"features":[{"code":"connectivity.usbcount2","label":"Antal USB 2.0 porte","value":"1"}],"label":"Antal USB 2.0 porte"},{"features":[{"code":"Color","label":"Produktfarve","value":"sort"}],"label":"Produktfarve"},{"features":[{"code":"TV.isWatchAndTimerFunctionOnOffPresent","label":"Ur og timerfunktion til\\/fra","value":"Ja"}],"label":"Ur og timerfunktion til\\/fra"},{"features":[{"code":"TV.isAutomaticChannelSearchAvailable","label":"Automatisk kanalsøgning","value":"Ja"}],"label":"Automatisk kanalsøgning"},{"features":[{"code":"screen.screenResolution","label":"Skærmopløsning","value":"Full-HD 1920 x 1080"}],"label":"Skærmopløsning"},{"features":[{"code":"TV.software","label":"TV software","value":"Android"}],"label":"TV software"},{"features":[{"code":"connectivity.connectivityDesc","label":"Andre tilslutningsmuligheder","value":"Composite, Audio in, VGA, optisk lyd ud,"}],"label":"Andre tilslutningsmuligheder"},{"features":[{"code":"TV.twinTuner","label":"Twin Tuner","value":"Nej"}],"label":"Twin Tuner"},{"features":[{"code":"picturePlayers.supportedVideoFileFormats","label":"Understøttede videofil formater","value":".MPG .MPEG.DAT.VOB.MKV.MP4 \\/ .M4A \\/ .M4V.MOV.FLV.3GP \\/ 3GPP.TS \\/ .M2TS.RMVB .RM.AVI.ASF .WMV.WEBM"}],"label":"Understøttede videofil formater"},{"features":[{"code":"isInternetBrowserPresent","label":"Internet browser","value":"Ja"}],"label":"Internet browser"},{"features":[{"code":"wirelessConnectivityOptionList","label":"Trådløse tilslutningsmuligheder","value":"Bluetooth"},{"code":"wirelessConnectivityOptionList","label":"Trådløse tilslutningsmuligheder","value":"Wi-Fi indbygget"}],"label":"Trådløse tilslutningsmuligheder"}]',step_product_id:"GR14425172",stock_count_online:2874,stock_count_status_online:"in_stock",stock_type:"NORMAL",summary:"Med Android og indbygget Chromecast",msg_sales_price_per_unit:l,package_display_sales_price:l,promotion_text:e,f_campaign_name:[]},loadingProduct:a}],error:e,state:{User:{UID:l,isLoggedIn:a,nickname:l,address:{firstName:l,lastName:l,address:l,postalCode:l,city:l,mobile:l,email:l,country:l},isDeliveryMethodSet:a,lastSeenProducts:[],wishlistProducts:[]},Tracking:{trackedOrders:[],activeRoute:e,oldRoute:e,cookieConsentGiven:a,initialRouteTracked:a},Search:{showDrawer:a,hideGlobalSearch:a,query:l,queryString:l,queries:[],brands:[],categories:[]},Products:{products:[]},ProductDialog:{showType:a,productId:e,quantity:e,error:e},plugins:{Cart:{checkoutErrorPlugin:{},productDialogPlugin:{}},TechnicalError:{technicalErrorPlugin:{}},Tracking:{gtmPlugin:{},gtmHandlers:{appInitializedHandler:{},bannerClickedHandler:{},bannerViewedHandler:{},checkoutStepChangedHandler:{},clickCollectCompletedHandler:{},cookieConsentGivenHandler:{},externalLinkClickedHandler:{},helpers:{},notFoundPageViewedHandler:{},orderCompletedHandler:{},plpProductsViewedHandler:{},productAddedHandler:{},productClickedHandler:{},productDetailViewedHandler:{},productQuantityChangeHandler:{},productRemovedHandler:{},recommendationsClickedHandler:{},recommendationsViewedHandler:{},routeChangedHandler:{},siteSearchHandler:{}}},User:{userPlugin:{}}},Payment:{paymentMethod:e,termsAccepted:a},OAuth:{accessToken:e,expiry:0,timestamp:e,trackingId:e},Navigation:{hierarchy:e,path:[],loading:a,lastFetchedTopNode:l},Layout:{eyebrow:{default:e},footer:{default:e},layout:s},InfoBar:{infoBars:[],infoBarMappers:{}},Delivery:{isFetchingPickups:a,deliveries:{},pickups:{},selectedDeliveries:{}},ClickCollect:{loading:a,showDrawer:a,baseMapLocation:e,stores:[],selectedStore:e,product:e,quantity:1,form:{name:l,email:l,countryDialCode:"45",phone:l,terms:a},reservation:e,error:a,filters:{inStockOnly:t}},Checkout:{panelState:{userInfo:{},delivery:{},payment:{mustVisit:t},store:{}},desiredPanel:"auto",panelValidators:{}},Cart:{data:{id:l,lineItems:[],totalLineItemsQuantity:0,totalSalesPrice:r,totalShippingSalesPrice:r,employeeNumber:e,loyaltyNumber:e,deliveries:[],totalLineItemSalesPrice:r,totalLineItemListPrice:r,totalLineItemDiscount:r,totalShippingListPrice:r,totalShippingPriceDiscount:r,orderNumber:e,totalSalesPriceNumber:0,isActive:t,isAllLineItemsValid:t,shippingAddress:d,billingAddress:d,hash:l,discountCodes:[],source:"USER_DEVICE"},loading:{},error:e,assistedSalesMode:a,assistedSalesStoreNumber:e},Breadcrumb:{categoryTree:{},productCategory:l,lookupBreadcrumbTasks:{},currentCategoryPage:[],helpers:{}}},serverRendered:t}}(null,"",!1,!0,"0,00","default","https://sg-dam.imgix.net/services/assets.img/id/87a045c1-0923-4575-81ce-fd9b7c3bfbf6/size/original","91052931-EA","100553115",void 0)
You can use a RegEx to get the Jsons from your string.
I have used this pattern: {(?:[^{}]*{[^{]*})*[^{}]*}
The above regex checks only the Json in one level deep.
Code:
import re
import json
input_data = """window.__NUXT__=funct ... A","100553115",void 0)"""
def json_validate(input_str):
founds = re.findall(r"{(?:[^{}]*{[^{]*})*[^{}]*}", input_str)
valid_jsons = []
for x in founds:
try:
valid_jsons.append(json.loads(x))
except json.JSONDecodeError:
continue
return valid_jsons
getting_jsons = json_validate(input_data)
for one_json in getting_jsons:
print(one_json)
print(len(getting_jsons))
It can find several (32) valid Jsons in your string:
>>> python3 test.py
{'features': [{'code': 'text-TvMemory', 'label': 'Tekst TV hukommelse', 'value': '1000'}], 'label': 'Tekst TV hukommelse'}
{'features': [{'code': 'tvFeatures', 'label': 'TV funktioner', 'value': 'Netflix'}, {'code': 'tvFeatures', 'label': 'TV funktioner', 'value': 'SmartTV'}, {'code': 'tvFeatures', 'label': 'TV funktioner', 'value': 'Wi-Fi indbygget'}], 'label': 'TV funktioner'}
{'features': [{'code': 'TV.tvApps', 'label': 'TV Apps', 'value': 'Amazon'}, {'code ...
I have found another solution which approaches the issue from totally different way: https://stackoverflow.com/a/54235803/11502612
I have tested the code from the above answer and I got the same output. It means the result is correct (probably).
Would it not be easier to do something like
import json
data = json.dumps(your_string)
Then iterate over it to find the values. Alternatively you can look for the value locations with
find("{")
Don't know if this is what your looking for but thought it may spark an idea / alternative view
I am trying to scrape data from a website for practicing web scraping.But the findall() returns empty set. How can I resolve this issue?
#importing required modules
import requests,bs4
#sending request to the server
req = requests.get("https://www.udemy.com/courses/search/?q=python")
# checking the status on the request
print(req.status_code)
req.raise_for_status()
#converting using BeautifulSoup
soup = bs4.BeautifulSoup(req.text,'html.parser')
#Trying to scrape the particular div with the class but returning 0
container = soup.find_all('div',class_='popover--popover--t3rNO popover--popover-hover--14ngr')
#trying to print the number of container returned.
print(len(container))
Output :
200
0
See my comment about it being entirely javascript driven content. Modern websites often will use javascript to invoke HTTP requests to the server to grab data on demand when needed. Here if you disable javascript which you can easily do in chrome by going to more settings when you inspect the page. You will see that NO text is available on this website. Which is probably much different to imdb as you pointed out. If you check the beautifulsoup parsed html, you'll see you don't have any of the actual page source derived with javascript.
There are two ways to get data from a javascript rendered website
Mimic the HTTP request to the server
Browser automation package like selenium
The first option is better and more efficient, as the second option is more brittle and not great for larger data sets.
Fortunately udemy is getting the data you want from an API endpoint which it uses javascript to make HTTP requests to and the response back gets fed to the browser.
Code Example
import requests
cookies = {
'__udmy_2_v57r': '4f711b308da548b49394854a189d3179',
'ud_firstvisit': '2020-05-29T13:48:56.584511+00:00:1jefNY:9F1BJVEUJpv7gmNPgYNini76UaE',
'existing_user': 'true',
'optimizelyEndUserId': 'oeu1590760136407r0.2130390415126655',
'EUCookieMessageShown': 'true',
'_ga': 'GA1.2.1359933509.1590760142',
'_pxvid': '26d89ed1-a1b3-11ea-9179-cb750fa4136b',
'_ym_uid': '1585144165890161851',
'_ym_d': '1590760145',
'__ssid': 'd191bc02a1063fd2c75fbab525ededc',
'stc111655': 'env:1592304425%7C20200717104705%7C20200616111705%7C1%7C1014616:20210616104705|uid:1590760145861.374775813.04725504.111655.1839745362:20210616104705|srchist:1069270%3A1%3A20200629134905%7C1014624%3A1592252104%3A20200716201504%7C1014616%3A1592304425%3A20200717104705:20210616104705|tsa:0:20200616111705',
'ki_t': '1590760146239%3B1592304425954%3B1592304425954%3B3%3B5',
'ki_r': 'aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8%3D',
'IR_PI': '00aea1e6-9da9-11ea-af3a-42010a24660a%7C1592390825988',
'_gac_UA-12366301-1': '1.1592304441.CjwKCAjw26H3BRB2EiwAy32zhfcltNEr_HHFK5JRaJar5qxUn4ifG9FVFctWyTUXigNZvKeOCz7PgxoCAfAQAvD_BwE',
'csrftoken': 'pPOdtdbH0HPaHvDfAZMzEOdvWqKZuQWufu8dUrEeXuy5mOOrnFRbWZ9vq8Dfd2ts',
'__cfruid': 'f1963d736e3891a2e307ebc9f918c89065ffe40f-1596962093',
'__cfduid': 'df4d951c87bc195c73b2f12b5e29568381597085850',
'ud_cache_price_country': 'GB',
'ud_cache_device': 'desktop',
'ud_cache_language': 'en',
'ud_cache_logged_in': '0',
'ud_cache_release': '0804b40d37e001f97dfa',
'ud_cache_modern_browser': '1',
'ud_cache_marketplace_country': 'GB',
'ud_cache_brand': 'GBen_US',
'ud_cache_version': '1',
'ud_cache_user': '',
'seen': '1',
'eventing_session_id': '66otW5O9TQWd5BYq1_etrA-1597087737933',
'ud_cache_campaign_code': '',
'exaff': '%7B%22start_date%22%3A%222020-08-09T08%3A52%3A04.083577Z%22%2C%22code%22%3A%22_7fFXpljNdk-m3_OJPaWBwAQc5gVKutaSg%22%2C%22merchant_id%22%3A39197%2C%22aff_type%22%3A%22LS%22%2C%22aff_id%22%3A60680%7D:1k5D3W:2PemPLTm4xaHixBYRvRyBaAukL4',
'evi': 'SlFfLh4RBzwTSVBjXFdHehNJUGMYQE99HVFdIExYQ3gARVY8QkAWIEEDCXsVQEd0BEsJexVAA24LQgdjGANXdgZBG3ETH1luRBdHKBoHV3ZKURl5XVBXdkpRXWNUU1luRxIJe1lTQXhMDgdjHRAFbgsICXNWVk1uCwgJN0xYRGATBUpjVFVEdAEOB2NcWkR+E0lQYxhAT30dUV0gTFhCfAhDVm1MUEJ0B1EROkwUV3YAXwk3D0BPewFAHzxCQEd0BUcJexVAA24LQgdjGANXdgZCHHETTld+BkUdY1QZVzoTSRptTBQUbgtFEnleHwhgEwBcY1QZV34HShtjVBlXOhNJE21MFBRuC0UceV4fWW4DSxh3TFgObkdREXBCQAMtE0kccFtUCGATQR54VkBPNxMFCXtfTlc6UFERd1tUTTEdURlzX1JXdkpRXWNUU1luRxIJe1tXQnpMXwlzVldDbgsICTdMWEdgEwVKY1RVRHUJDgdjXFdCdBNJUGMYQE99HVFdIExYQ3kCQ1Y8Ew==',
'ud_rule_vars': 'eJyFjkuOwyAQBa9isZ04agyYz1ksIYxxjOIRGmhPFlHuHvKVRrPItvWqus4EXT4EDJP9jSViyobPktKRgZqc4GrkmmmuBHdU6YlRqY1P6RgDMQ05D2SOueCDtZPDMNT7QDrooAXRdrqhzHBlRL8XUjPgXwAGYCC7ulpdRX3acglPA8bvPwbVgm6g4p0Bvqeyhsh_BkybXyxmN8_R21J9vvpcjm5cn7ZDTidc7G2xxnvlm87hZwvlU7wE2VP1en0hlyuoG10j:1k5D3W:nxRv-tyLU7lxhsF2jRYvkJA53uM',
}
headers = {
'authority': 'www.udemy.com',
'x-udemy-cache-release': '0804b40d37e001f97dfa',
'x-udemy-cache-language': 'en',
'x-udemy-cache-user': '',
'x-udemy-cache-modern-browser': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36',
'accept': 'application/json, text/plain, */*',
'x-udemy-cache-brand': 'GBen_US',
'x-udemy-cache-version': '1',
'x-requested-with': 'XMLHttpRequest',
'x-udemy-cache-logged-in': '0',
'x-udemy-cache-price-country': 'GB',
'x-udemy-cache-device': 'desktop',
'x-udemy-cache-marketplace-country': 'GB',
'x-udemy-cache-campaign-code': '',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://www.udemy.com/courses/search/?q=python',
'accept-language': 'en-US,en;q=0.9',
}
params = (
('q', 'python'),
('skip_price', 'false'),
)
response = requests.get('https://www.udemy.com/api-2.0/search-courses/', headers=headers, params=params, cookies=cookies)
ids = []
titles = []
durations = []
ratings = []
for a in response.json()['courses']:
title = a['title']
duration =int(a['estimated_content_length']) / 60
rating = a['rating']
id = str(a['id'])
titles.append(title)
ids.append(id)
durations.append(duration)
ratings.append(rating)
clean_ids = ','.join(ids)
params2 = (
('course_ids', clean_ids),
('fields/[pricing_result/]', 'price,discount_price,list_price,price_detail,price_serve_tracking_id'),
)
response = requests.get('https://www.udemy.com/api-2.0/pricing/', params=params2)
data = response.json()['courses']
prices = []
for a in ids:
price = response.json()['courses'][a]['price']['amount']
prices.append(price)
data = zip(titles, durations,ratings, prices)
for a in data:
print(a)
Output
('Learn Python Programming Masterclass', 56.53333333333333, 4.54487, 14.99)
('The Python Mega Course: Build 10 Real World Applications', 25.3, 4.51476, 16.99)
('Python for Beginners: Learn Python Programming (Python 3)', 2.8833333333333333, 4.4391, 17.99)
('The Python Bible™ | Everything You Need to Program in Python', 9.15, 4.64238, 17.99)
('Python for Absolute Beginners', 3.066666666666667, 4.42209, 14.99)
('The Modern Python 3 Bootcamp', 30.3, 4.64714, 16.99)
('Python for Finance: Investment Fundamentals & Data Analytics', 8.25, 4.52908, 12.99)
('The Complete Python Course | Learn Python by Doing', 35.31666666666667, 4.58885, 17.99)
('REST APIs with Flask and Python', 17.033333333333335, 4.61233, 12.99)
('Python for Financial Analysis and Algorithmic Trading', 16.916666666666668, 4.53173, 12.99)
('Python for Beginners with Examples', 4.25, 4.27316, 12.99)
('Python OOP : Four Pillars of OOP in Python 3 for Beginners', 2.6166666666666667, 4.46451, 12.99)
('Python Bootcamp 2020 Build 15 working Applications and Games', 32.13333333333333, 4.2519, 14.99)
('The Complete Python Masterclass: Learn Python From Scratch', 32.36666666666667, 4.39151, 16.99)
('Learn Python MADE EASY : A Concise Python Course in Python 3', 2.1166666666666667, 4.76601, 12.99)
('Complete Python Web Course: Build 8 Python Web Apps', 15.65, 4.37577, 13.99)
('Python for Excel: Use xlwings for Data Science and Finance', 16.116666666666667, 4.92293, 12.99)
('Python 3 Network Programming - Build 5 Network Applications', 12.216666666666667, 4.66143, 12.99)
('The Complete Python & PostgreSQL Developer Course', 21.833333333333332, 4.5664, 12.99)
('The Complete Python Programmer Bootcamp 2020', 13.233333333333333, 4.63859, 12.99)
Explanation
There are two ways to do this, here is re-engineering the requests which is the more efficient solution. To get the necessary information, you'll need to inspect the page and look at which HTTP requests give which information. You can do this through the network tools --> XHR when you inspect the page. You can see there are two requests that give you information. My suggestion would be look at the previews of the responses on the right hand side when you select the request. The first gives you the title, duration, price, ratings and the second request you need the id's of the courses to get the prices of the courses.
I usually copy the CURL of the HTTP requests the javascript invokes into curl.trillworks.com and this converts the necessary headers, parameters and cookies to python format.
In the first request, headers, cookies and parameters are required. THe second request, only requires the parameters.
The response you get is a json object. response.json() converts this into a python dictionary. You have to do abit of digging in this dictionary to get what you want. But for each item in response.json()['courses'] all the necessary data for each 'card' on the website is there. So we do a for loop around where the data sits in the dictionary we've created. I would play around the with response.json() till you get a feel for what the object gives you to understand the code.
The duration comes in minutes therefore I've done a quick convert to hours here. Also the id's need to be a string because in the second request we use them as parameters to get the necessary prices for the courses. We convert ids into a string and feed this as a parameter.
The second request then gives us the necessary prices, again you have to go digging in the dictionary object and I suggest you do this yourself to confirm that nested in that is the price.
The data we zip up to combine all the lists of data and then I've done a for loop to print it all. You could feed this into pandas if you wanted etc...
To get required data you need to send requests to appropriate API. For that you need to create Session:
import requests
s = requests.Session()
cookies = s.get('https://www.udemy.com').cookies
headers={"Referer": "https://www.udemy.com/courses/search/?q=python&skip_price=false"}
for page_counter in range(1, 500):
data = s.get('https://www.udemy.com/api-2.0/search-courses/?p={}&q=python&skip_price=false'.format(page_counter), cookies=cookies, headers=headers).json()
for course in data['courses']:
params = {'course_ids': [str(course['id']),],
'fields/[pricing_result/]': ['price',]}
title = course['title']
price = s.get('https://www.udemy.com/api-2.0/pricing/', params=params, cookies=cookies).json()['courses'][str(course['id'])]['price']['amount']
print({'title': title, 'price': price})
i am using geopy library for my Flask web app. i want to save user location which i am getting from my modal(html form) in my database(i am using mongodb), but every single time i am getting this error:
TypeError: Object of type 'Location' is not JSON serializable
Here's the code:
#app.route('/register', methods=['GET', 'POST'])
def register_user():
if request.method == 'POST':
login_user = mongo.db.mylogin
existing_user = login_user.find_one({'email': request.form['email']})
# final_location = geolocator.geocode(session['address'].encode('utf-8'))
if existing_user is None:
hashpass = bcrypt.hashpw(
request.form['pass'].encode('utf-8'), bcrypt.gensalt())
login_user.insert({'name': request.form['username'], 'email': request.form['email'], 'password': hashpass, 'address': request.form['add'], 'location' : session['location'] })
session['password'] = request.form['pass']
session['username'] = request.form['username']
session['address'] = request.form['add']
session['location'] = geolocator.geocode(session['address'])
flash(f"You are Registerd as {session['username']}")
return redirect(url_for('home'))
flash('Username is taken !')
return redirect(url_for('home'))
return render_template('index.html')
Please Help, let me know if you want more info..
According to the geolocator documentation the geocode function "Return a location point by address" geopy.location.Location objcet.
Json serialize support by default the following types:
Python | JSON
dict | object
list, tuple | array
str, unicode | string
int, long, float | number
True | true
False | false
None | null
All the other objects/types are not json serialized by default and there for you need to defined it.
geopy.location.Location.raw
Location’s raw, unparsed geocoder response. For details on this,
consult the service’s documentation.
Return type: dict or None
You might be able to call the raw function of the Location (the geolocator.geocode return value) and this value will be json serializable.
Location is indeed not json serializable: there are many properties in this object and there is no single way to represent a location, so you'd have to choose one by yourself.
What type of value do you expect to see in the location key of the response?
Here are some examples:
Textual address
In [9]: json.dumps({'location': geolocator.geocode("175 5th Avenue NYC").address})
Out[9]: '{"location": "Flatiron Building, 175, 5th Avenue, Flatiron District, Manhattan Community Board 5, Manhattan, New York County, New York, 10010, United States of America"}'
Point coordinates
In [10]: json.dumps({'location': list(geolocator.geocode("175 5th Avenue NYC").point)})
Out[10]: '{"location": [40.7410861, -73.9896298241625, 0.0]}'
Raw Nominatim response
(That's probably not what you want to expose in your API, assuming you want to preserve an ability to change geocoding service to another one in future, which might have a different raw response schema).
In [11]: json.dumps({'location': geolocator.geocode("175 5th Avenue NYC").raw})
Out[11]: '{"location": {"place_id": 138642704, "licence": "Data \\u00a9 OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright", "osm_type": "way", "osm_id": 264768896, "boundingbox": ["40.7407597", "40.7413004", "-73.9898715", "-73.9895014"], "lat": "40.7410861", "lon": "-73.9896298241625", "display_name": "Flatiron Building, 175, 5th Avenue, Flatiron District, Manhattan Community Board 5, Manhattan, New York County, New York, 10010, United States of America", "class": "tourism", "type": "attraction", "importance": 0.74059885426854, "icon": "https://nominatim.openstreetmap.org/images/mapicons/poi_point_of_interest.p.20.png"}}'
Textual address + point coordinates
In [12]: location = geolocator.geocode("175 5th Avenue NYC")
...: json.dumps({'location': {
...: 'address': location.address,
...: 'point': list(location.point),
...: }})
Out[12]: '{"location": {"address": "Flatiron Building, 175, 5th Avenue, Flatiron District, Manhattan Community Board 5, Manhattan, New York County, New York, 10010, United States of America", "point": [40.7410861, -73.9896298241625, 0.0]}}'