extracting JSON from from an http request response - Scrapy - python

I'm building a web scraper to extract product information from the product link.
the web url is the following: https://scrapingclub.com/exercise/detail_header/
I found the HTTP request link for product details with chrome Dev Tools.
This is my code
class quoteSpider(scrapy.Spider):
name = 'Practice'
start_urls = ['https://scrapingclub.com/exercise/detail_header/']
def parse(self,response):
yield scrapy.Request('https://scrapingclub.com/exercise/ajaxdetail_header/', callback = self.parse_detail, headers={'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'es-ES,es;q=0.9,pt;q=0.8',
'Connection': 'keep-alive',
'Cookie': '__cfduid=da54d7e9c59cf35860825eabc96d7f1c41612805624; _ga=GA1.2.1229230175.1612805628; _gid=GA1.2.205529574.1613135874',
'Host': 'scrapingclub.com',
'Referer': 'https://scrapingclub.com/exercise/detail_header/',
'sec-ch-ua': '"Chromium";v="88", "Google Chrome";v="88", ";Not A Brand";v="99"',
'sec-ch-ua-mobile': '?0',
'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/88.0.4324.150 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest'})
def parse_detail(self, response):
product = ProductClass()
data = response
# im still debugging so im not putting it into an item yet
# data = json.loads(response.text)
# product['product_name'] = data['title']
# product['detail'] = data['description']
# product['price'] = data['price']
yield {
'value' : data
}
When I run
scrapy crawl ProductSpider -O test.json
This is my output file
[
{"value": "<TextResponse 200 https://scrapingclub.com/exercise/ajaxdetail_header/>"}
]
Why isn't returning me the JSON content?


change header data to get the expected output
class quoteSpider(scrapy.Spider):
name = 'Practice'
start_urls = ['https://scrapingclub.com/exercise/detail_header/']
def parse(self,response):
headers = {
'authority': 'scrapingclub.com',
'accept': '*/*',
'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://scrapingclub.com/exercise/detail_header/',
'accept-language': 'en-US,en;q=0.9',
'cookie': '__cfduid=d69d9664405f96c6477078a5c1fa78bb41613195439; _ga=GA1.2.523835360.1613195440; _gid=GA1.2.1763722170.1613195440',
}
yield scrapy.Request('https://scrapingclub.com/exercise/ajaxdetail_header/',
callback = self.parse_detail, headers=headers)
def parse_detail(self, response):
product = {}
data = response
# im still debugging so im not putting it into an item yet
data = json.loads(response.text)
product['product_name'] = data['title']
product['detail'] = data['description']
product['price'] = data['price']
yield product

Related

Scraping data through Api from json

I would like to limit the data they receive to the first 8 links on the website. As shown in the picture, there is no data available beyond the 8th link, as seen in the CSV file. How can I apply this limit so that they only receive data from the first 8 links? The website link is https://www.linkedin.com/learning/search?keywords=data%20science,
JSON API
CSV File
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')

To filter the rows that contain empty columns, specifically those with an empty title column, you can simply add the following code:
df=pd.DataFrame(product)
filter = df["title"] != ""
dfNew = df[filter]
dfNew.to_csv('learning.csv')
The entire code will be:
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=''
name = item.get("description", {}).get("text", "")
wev={
'title':title,
'instructor':name,
'review':rating,
'url':url
}
product.append(wev)
df=pd.DataFrame(product)
filter = df["title"] != ""
dfNew = df[filter]
dfNew.to_csv('learning.csv')
However, this is solution works because the web is structured. For complex/irregular websites I prefer to use scrapy as we use in my job.

Added code and now it's not print correctly to CSV file

I have the first code that is working and printing to csv, however it included a lot of data I didn't need. A paragraph of code was then added to only include the data I wanted. The problem is it prints to the screen correctly but still includes all the data in the CSV file. I've tried everything I could think of in this line but it won't either won't print or still prints everything.
data = pd.DataFrame(stock_info)
Could someone show me where I'm going wrong so it will print only the portion I want it to?
Old Working Code
import requests
import pandas as pd
url = "https://www.stockrover.com/stock_infos/grid?_dc=1644769629231"
def stock_data(stock_info):
data = pd.DataFrame(stock_info)
data.to_csv("data.csv", index=False)
payload = "state=%7B%22sortInfo%22%3A%7B%7D%2C%22columns%22%3A%5B77%2C32%2C498%2C500%2C31%2C27%2C499%2C30%2C578%2C28%2C29%2C544%2C181%2C185%2C186%5D%2C%22view%22%3A281%2C%22priorPrimaryColumn%22%3A170%2C%22filterData%22%3A%5B%5D%2C%22name%22%3A%22New%201%22%2C%22cType%22%3A%22Screener%22%2C%22cNode%22%3A%22s_39%22%2C%22cIsFolder%22%3Afalse%2C%22gridSelection%22%3A%22BTU%22%2C%22lastActive%22%3A1396898415%2C%22primaryColumn%22%3A76%2C%22folderDisabledParams%22%3A%7B%22filterData%22%3A%5B%5D%7D%2C%22mainGridDateRange%22%3A%22ytd%22%2C%22groupState%22%3Anull%2C%22moversGridDateRange%22%3A%221_day%22%2C%22peersGridDateRange%22%3A%221_day%22%2C%22lastGridSelections%22%3A%5B%22BTU%22%5D%2C%22lastQuantNode%22%3A%5B%5D%2C%22includeQuotesInTable%22%3Afalse%2C%22includeAllQuotesLastValue%22%3Afalse%2C%22markets%22%3A%7B%22panel%22%3A%22summary%22%7D%2C%22researchPanel%22%3A%22tablePanel%22%2C%22recentSearchTickers%22%3A%5B%22SPY%22%2C%22AMZN%22%2C%22AAPL%22%2C%22s_32%22%2C%22%5ENDX%22%2C%22AXP%22%2C%22XOM%22%2C%22AFL%22%2C%22%5EDJX%22%2C%22AIT%22%2C%22ADVC%22%5D%2C%22quotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22checkedQuotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22dashboard%22%3A%7B%22buttonRef%22%3A%22272%22%7D%2C%22tickerSelectedFeeds%22%3A%5B%22Benzinga%20News%22%2C%22Yahoo%20News%22%5D%2C%22marketSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Stock%20Market%20News%20-%20Investing.com%22%5D%2C%22bondsSelectedFeeds%22%3A%5B%22Bonds%20Strategy%20-%20Investing.com%22%5D%2C%22commoditiesSelectedFeeds%22%3A%5B%22Commodities%20%26%20Futures%20News%20-%20Investing.com%22%2C%22Commodities%20Fundamental%20Analysis%20-%20Investing.com%22%2C%22Commodities%20Strategy%20Analysis%20-%20Investing.com%22%5D%2C%22stocksSelectedFeeds%22%3A%5B%22CNNMoney%20News%22%2C%22Google%20News%22%2C%22Seeking%20Alpha%20Top%20Stories%22%5D%2C%22etfsSelectedFeeds%22%3A%5B%22Economy%20News%20-%20Investing.com%22%2C%22ETF%20Analysis%20-%20Investing.com%22%2C%22Investing%20Ideas%20-%20Investing.com%22%5D%2C%22topPanel%22%3A%22researchPanel%22%2C%22maxRecordsNode%22%3Afalse%2C%22version%22%3A7%2C%22lastGridSelectionsRaw%22%3A%5B%22BTU%22%5D%2C%22lastSelectionScreeners%22%3A%22s_39%22%2C%22quotesDisabled%22%3Atrue%2C%22lastSelectionPortfolios%22%3A%22p_2%22%2C%22comparisonPanels%22%3A%7B%22Portfolio%22%3A%22p_2%22%2C%22Index%22%3A%22%5EDJX%22%2C%22Watchlist%22%3A%22Watchlists%22%2C%22Screener%22%3A%22s_39%22%7D%2C%22lastSelectionWatchlists%22%3A%22w_26%22%2C%22indicesSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Yahoo%20News%22%5D%2C%22newsActive%22%3A%22tickerNews%22%2C%22recentSearchMetrics%22%3A%5B%22Price%22%2C%22EPS%22%2C%22Sales%22%5D%2C%22editPanel%22%3A%22positionsPanel%22%2C%22newsType%22%3A%22marketNews%22%2C%22tableColumns%22%3A%5B%22ticker%22%2C%22rank%22%2C%22score_rank%22%2C%22filter_score%22%2C%22company%22%2C%22cash%22%2C%22currentassets%22%2C%22netppe%22%2C%22intangibles%22%2C%22totalassets%22%2C%22currentliabilities%22%2C%22longtermdebt%22%2C%22totaldebt%22%2C%22totalliabilities%22%2C%22equity%22%2C%22tangiblebookvalue%22%2C%22cash_short_term_p%22%2C%22net_ppe_p%22%2C%22intangibles_p%22%5D%2C%22last_save%22%3A1644769379%2C%22panels%22%3A%7B%22collapsed%22%3A%7B%22chp%22%3Atrue%2C%22ip%22%3Atrue%2C%22mp%22%3Afalse%2C%22qp%22%3Afalse%2C%22conp%22%3Atrue%2C%22fsp%22%3Afalse%7D%2C%22viewportWidth%22%3A%221920%22%2C%22viewportHeight%22%3A%221069%22%2C%22chartPanelHeight%22%3A483%2C%22controlPanelWidth%22%3A296%2C%22insightPanelWidth%22%3A%22485%22%2C%22quoteBoxHeight%22%3A200%2C%22navigationPanelWidth%22%3A277%7D%7D&updateMarket=true&page=1&start=0&limit=250"
headers = {
'authority': 'www.stockrover.com',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="98", "Google Chrome";v="98"',
'x-csrf-token': '7yR4pfI0kAArtjJak535+NJrpB0L212PAbXCg0kbyE4SyjFaQ73sMHJLiqAkPb5nGzfC8KvAa3kTADLAEQXyOQ==',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36',
'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'accept': 'application/json',
'x-requested-with': 'XMLHttpRequest',
'sec-ch-ua-platform': '"Windows"',
'origin': 'https://www.stockrover.com',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://www.stockrover.com/research/table/281/s_39/BTU',
'accept-language': 'en-US,en;q=0.9',
'cookie': 'remember_me_pref=0; user_name=test11964; plan=3; premiumBraintreeKey=MIIBCgKCAQEAzM4LJfrNnBOgRFB1dDJkmqTFCWT2Y%2BksOydD8xDH4R033WUzxbffMZb%2B3dqEyQvOVjLcwFIHByDc4Xwej7enas2E%2FVRyh7Cvyadn7M5zQeRyLcI9Ys5KCozMwxJPc0x76FlXPwiAo1Qlz3RcLb9wGHBag2R51FuTie%2BhVDCgzWajqDCREzRhi%2Fqlt3D%2FxXNo%2FiwJlpOUr%2Fx1QnkkILxgKlq1dD7KJ767O5ojYKXsO%2BV2Bfu7sSD3djsOxQJ1%2FRbaDm2E96EDkWhhOeOpPndQ6IuSl4NmnJg%2Fcq6f8csW8M3Ys%2BMZPFkdxPC4%2FfRM1XC9o76PjpVNBIO%2ByJEELKZedwIDAQAB; lr=1644769628; _Ruby2_session=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%3D--1439f36a7f9362aee4b5b666747a2d63d72e81bd'
}
response = requests.request("POST", url, headers=headers, data=payload)
stock_info = response.json()['stock_infos']
stock_data(stock_info)
New Non-Working Code
import requests
import pandas as pd
url = "https://www.stockrover.com/stock_infos/grid?_dc=1644769629231"
def stock_data(stock_info):
data = pd.DataFrame(stock_info)
data.to_csv("data.csv", index=False)
payload = "state=%7B%22sortInfo%22%3A%7B%7D%2C%22columns%22%3A%5B77%2C32%2C498%2C500%2C31%2C27%2C499%2C30%2C578%2C28%2C29%2C544%2C181%2C185%2C186%5D%2C%22view%22%3A281%2C%22priorPrimaryColumn%22%3A170%2C%22filterData%22%3A%5B%5D%2C%22name%22%3A%22New%201%22%2C%22cType%22%3A%22Screener%22%2C%22cNode%22%3A%22s_39%22%2C%22cIsFolder%22%3Afalse%2C%22gridSelection%22%3A%22BTU%22%2C%22lastActive%22%3A1396898415%2C%22primaryColumn%22%3A76%2C%22folderDisabledParams%22%3A%7B%22filterData%22%3A%5B%5D%7D%2C%22mainGridDateRange%22%3A%22ytd%22%2C%22groupState%22%3Anull%2C%22moversGridDateRange%22%3A%221_day%22%2C%22peersGridDateRange%22%3A%221_day%22%2C%22lastGridSelections%22%3A%5B%22BTU%22%5D%2C%22lastQuantNode%22%3A%5B%5D%2C%22includeQuotesInTable%22%3Afalse%2C%22includeAllQuotesLastValue%22%3Afalse%2C%22markets%22%3A%7B%22panel%22%3A%22summary%22%7D%2C%22researchPanel%22%3A%22tablePanel%22%2C%22recentSearchTickers%22%3A%5B%22SPY%22%2C%22AMZN%22%2C%22AAPL%22%2C%22s_32%22%2C%22%5ENDX%22%2C%22AXP%22%2C%22XOM%22%2C%22AFL%22%2C%22%5EDJX%22%2C%22AIT%22%2C%22ADVC%22%5D%2C%22quotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22checkedQuotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22dashboard%22%3A%7B%22buttonRef%22%3A%22272%22%7D%2C%22tickerSelectedFeeds%22%3A%5B%22Benzinga%20News%22%2C%22Yahoo%20News%22%5D%2C%22marketSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Stock%20Market%20News%20-%20Investing.com%22%5D%2C%22bondsSelectedFeeds%22%3A%5B%22Bonds%20Strategy%20-%20Investing.com%22%5D%2C%22commoditiesSelectedFeeds%22%3A%5B%22Commodities%20%26%20Futures%20News%20-%20Investing.com%22%2C%22Commodities%20Fundamental%20Analysis%20-%20Investing.com%22%2C%22Commodities%20Strategy%20Analysis%20-%20Investing.com%22%5D%2C%22stocksSelectedFeeds%22%3A%5B%22CNNMoney%20News%22%2C%22Google%20News%22%2C%22Seeking%20Alpha%20Top%20Stories%22%5D%2C%22etfsSelectedFeeds%22%3A%5B%22Economy%20News%20-%20Investing.com%22%2C%22ETF%20Analysis%20-%20Investing.com%22%2C%22Investing%20Ideas%20-%20Investing.com%22%5D%2C%22topPanel%22%3A%22researchPanel%22%2C%22maxRecordsNode%22%3Afalse%2C%22version%22%3A7%2C%22lastGridSelectionsRaw%22%3A%5B%22BTU%22%5D%2C%22lastSelectionScreeners%22%3A%22s_39%22%2C%22quotesDisabled%22%3Atrue%2C%22lastSelectionPortfolios%22%3A%22p_2%22%2C%22comparisonPanels%22%3A%7B%22Portfolio%22%3A%22p_2%22%2C%22Index%22%3A%22%5EDJX%22%2C%22Watchlist%22%3A%22Watchlists%22%2C%22Screener%22%3A%22s_39%22%7D%2C%22lastSelectionWatchlists%22%3A%22w_26%22%2C%22indicesSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Yahoo%20News%22%5D%2C%22newsActive%22%3A%22tickerNews%22%2C%22recentSearchMetrics%22%3A%5B%22Price%22%2C%22EPS%22%2C%22Sales%22%5D%2C%22editPanel%22%3A%22positionsPanel%22%2C%22newsType%22%3A%22marketNews%22%2C%22tableColumns%22%3A%5B%22ticker%22%2C%22rank%22%2C%22score_rank%22%2C%22filter_score%22%2C%22company%22%2C%22cash%22%2C%22currentassets%22%2C%22netppe%22%2C%22intangibles%22%2C%22totalassets%22%2C%22currentliabilities%22%2C%22longtermdebt%22%2C%22totaldebt%22%2C%22totalliabilities%22%2C%22equity%22%2C%22tangiblebookvalue%22%2C%22cash_short_term_p%22%2C%22net_ppe_p%22%2C%22intangibles_p%22%5D%2C%22last_save%22%3A1644769379%2C%22panels%22%3A%7B%22collapsed%22%3A%7B%22chp%22%3Atrue%2C%22ip%22%3Atrue%2C%22mp%22%3Afalse%2C%22qp%22%3Afalse%2C%22conp%22%3Atrue%2C%22fsp%22%3Afalse%7D%2C%22viewportWidth%22%3A%221920%22%2C%22viewportHeight%22%3A%221069%22%2C%22chartPanelHeight%22%3A483%2C%22controlPanelWidth%22%3A296%2C%22insightPanelWidth%22%3A%22485%22%2C%22quoteBoxHeight%22%3A200%2C%22navigationPanelWidth%22%3A277%7D%7D&updateMarket=true&page=1&start=0&limit=250"
headers = {
'authority': 'www.stockrover.com',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="98", "Google Chrome";v="98"',
'x-csrf-token': '7yR4pfI0kAArtjJak535+NJrpB0L212PAbXCg0kbyE4SyjFaQ73sMHJLiqAkPb5nGzfC8KvAa3kTADLAEQXyOQ==',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36',
'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'accept': 'application/json',
'x-requested-with': 'XMLHttpRequest',
'sec-ch-ua-platform': '"Windows"',
'origin': 'https://www.stockrover.com',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://www.stockrover.com/research/table/281/s_39/BTU',
'accept-language': 'en-US,en;q=0.9',
'cookie': 'remember_me_pref=0; user_name=test11964; plan=3; premiumBraintreeKey=MIIBCgKCAQEAzM4LJfrNnBOgRFB1dDJkmqTFCWT2Y%2BksOydD8xDH4R033WUzxbffMZb%2B3dqEyQvOVjLcwFIHByDc4Xwej7enas2E%2FVRyh7Cvyadn7M5zQeRyLcI9Ys5KCozMwxJPc0x76FlXPwiAo1Qlz3RcLb9wGHBag2R51FuTie%2BhVDCgzWajqDCREzRhi%2Fqlt3D%2FxXNo%2FiwJlpOUr%2Fx1QnkkILxgKlq1dD7KJ767O5ojYKXsO%2BV2Bfu7sSD3djsOxQJ1%2FRbaDm2E96EDkWhhOeOpPndQ6IuSl4NmnJg%2Fcq6f8csW8M3Ys%2BMZPFkdxPC4%2FfRM1XC9o76PjpVNBIO%2ByJEELKZedwIDAQAB; lr=1644769628; _Ruby2_session=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%3D--1439f36a7f9362aee4b5b666747a2d63d72e81bd'
}
response = requests.request("POST", url, headers=headers, data=payload)
stock_info = response.json()['stock_infos']
stock_data(stock_info)
for info in stock_info:
key = info[0]
for i, sub in enumerate(info[1:], 1):
if sub == key:
print(info[i:])
break

If you don't need to keep those columns just slice them out by adding a line to your original code:
data = pd.DataFrame(stock_info)
data = data.iloc[:, 4:]
In original code:
import requests
import pandas as pd
url = "https://www.stockrover.com/stock_infos/grid?_dc=1644769629231"
def stock_data(stock_info):
data = pd.DataFrame(stock_info)
data = data.iloc[:, 4:]
data.to_csv("data.csv", index=False)
payload = "state=%7B%22sortInfo%22%3A%7B%7D%2C%22columns%22%3A%5B77%2C32%2C498%2C500%2C31%2C27%2C499%2C30%2C578%2C28%2C29%2C544%2C181%2C185%2C186%5D%2C%22view%22%3A281%2C%22priorPrimaryColumn%22%3A170%2C%22filterData%22%3A%5B%5D%2C%22name%22%3A%22New%201%22%2C%22cType%22%3A%22Screener%22%2C%22cNode%22%3A%22s_39%22%2C%22cIsFolder%22%3Afalse%2C%22gridSelection%22%3A%22BTU%22%2C%22lastActive%22%3A1396898415%2C%22primaryColumn%22%3A76%2C%22folderDisabledParams%22%3A%7B%22filterData%22%3A%5B%5D%7D%2C%22mainGridDateRange%22%3A%22ytd%22%2C%22groupState%22%3Anull%2C%22moversGridDateRange%22%3A%221_day%22%2C%22peersGridDateRange%22%3A%221_day%22%2C%22lastGridSelections%22%3A%5B%22BTU%22%5D%2C%22lastQuantNode%22%3A%5B%5D%2C%22includeQuotesInTable%22%3Afalse%2C%22includeAllQuotesLastValue%22%3Afalse%2C%22markets%22%3A%7B%22panel%22%3A%22summary%22%7D%2C%22researchPanel%22%3A%22tablePanel%22%2C%22recentSearchTickers%22%3A%5B%22SPY%22%2C%22AMZN%22%2C%22AAPL%22%2C%22s_32%22%2C%22%5ENDX%22%2C%22AXP%22%2C%22XOM%22%2C%22AFL%22%2C%22%5EDJX%22%2C%22AIT%22%2C%22ADVC%22%5D%2C%22quotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22checkedQuotesBoxTickers%22%3A%5B%22AMZN%22%2C%22AAPL%22%2C%22SPY%22%5D%2C%22dashboard%22%3A%7B%22buttonRef%22%3A%22272%22%7D%2C%22tickerSelectedFeeds%22%3A%5B%22Benzinga%20News%22%2C%22Yahoo%20News%22%5D%2C%22marketSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Stock%20Market%20News%20-%20Investing.com%22%5D%2C%22bondsSelectedFeeds%22%3A%5B%22Bonds%20Strategy%20-%20Investing.com%22%5D%2C%22commoditiesSelectedFeeds%22%3A%5B%22Commodities%20%26%20Futures%20News%20-%20Investing.com%22%2C%22Commodities%20Fundamental%20Analysis%20-%20Investing.com%22%2C%22Commodities%20Strategy%20Analysis%20-%20Investing.com%22%5D%2C%22stocksSelectedFeeds%22%3A%5B%22CNNMoney%20News%22%2C%22Google%20News%22%2C%22Seeking%20Alpha%20Top%20Stories%22%5D%2C%22etfsSelectedFeeds%22%3A%5B%22Economy%20News%20-%20Investing.com%22%2C%22ETF%20Analysis%20-%20Investing.com%22%2C%22Investing%20Ideas%20-%20Investing.com%22%5D%2C%22topPanel%22%3A%22researchPanel%22%2C%22maxRecordsNode%22%3Afalse%2C%22version%22%3A7%2C%22lastGridSelectionsRaw%22%3A%5B%22BTU%22%5D%2C%22lastSelectionScreeners%22%3A%22s_39%22%2C%22quotesDisabled%22%3Atrue%2C%22lastSelectionPortfolios%22%3A%22p_2%22%2C%22comparisonPanels%22%3A%7B%22Portfolio%22%3A%22p_2%22%2C%22Index%22%3A%22%5EDJX%22%2C%22Watchlist%22%3A%22Watchlists%22%2C%22Screener%22%3A%22s_39%22%7D%2C%22lastSelectionWatchlists%22%3A%22w_26%22%2C%22indicesSelectedFeeds%22%3A%5B%22Google%20News%22%2C%22Yahoo%20News%22%5D%2C%22newsActive%22%3A%22tickerNews%22%2C%22recentSearchMetrics%22%3A%5B%22Price%22%2C%22EPS%22%2C%22Sales%22%5D%2C%22editPanel%22%3A%22positionsPanel%22%2C%22newsType%22%3A%22marketNews%22%2C%22tableColumns%22%3A%5B%22ticker%22%2C%22rank%22%2C%22score_rank%22%2C%22filter_score%22%2C%22company%22%2C%22cash%22%2C%22currentassets%22%2C%22netppe%22%2C%22intangibles%22%2C%22totalassets%22%2C%22currentliabilities%22%2C%22longtermdebt%22%2C%22totaldebt%22%2C%22totalliabilities%22%2C%22equity%22%2C%22tangiblebookvalue%22%2C%22cash_short_term_p%22%2C%22net_ppe_p%22%2C%22intangibles_p%22%5D%2C%22last_save%22%3A1644769379%2C%22panels%22%3A%7B%22collapsed%22%3A%7B%22chp%22%3Atrue%2C%22ip%22%3Atrue%2C%22mp%22%3Afalse%2C%22qp%22%3Afalse%2C%22conp%22%3Atrue%2C%22fsp%22%3Afalse%7D%2C%22viewportWidth%22%3A%221920%22%2C%22viewportHeight%22%3A%221069%22%2C%22chartPanelHeight%22%3A483%2C%22controlPanelWidth%22%3A296%2C%22insightPanelWidth%22%3A%22485%22%2C%22quoteBoxHeight%22%3A200%2C%22navigationPanelWidth%22%3A277%7D%7D&updateMarket=true&page=1&start=0&limit=250"
headers = {
'authority': 'www.stockrover.com',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="98", "Google Chrome";v="98"',
'x-csrf-token': '7yR4pfI0kAArtjJak535+NJrpB0L212PAbXCg0kbyE4SyjFaQ73sMHJLiqAkPb5nGzfC8KvAa3kTADLAEQXyOQ==',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36',
'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'accept': 'application/json',
'x-requested-with': 'XMLHttpRequest',
'sec-ch-ua-platform': '"Windows"',
'origin': 'https://www.stockrover.com',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://www.stockrover.com/research/table/281/s_39/BTU',
'accept-language': 'en-US,en;q=0.9',
'cookie': 'remember_me_pref=0; user_name=test11964; plan=3; premiumBraintreeKey=MIIBCgKCAQEAzM4LJfrNnBOgRFB1dDJkmqTFCWT2Y%2BksOydD8xDH4R033WUzxbffMZb%2B3dqEyQvOVjLcwFIHByDc4Xwej7enas2E%2FVRyh7Cvyadn7M5zQeRyLcI9Ys5KCozMwxJPc0x76FlXPwiAo1Qlz3RcLb9wGHBag2R51FuTie%2BhVDCgzWajqDCREzRhi%2Fqlt3D%2FxXNo%2FiwJlpOUr%2Fx1QnkkILxgKlq1dD7KJ767O5ojYKXsO%2BV2Bfu7sSD3djsOxQJ1%2FRbaDm2E96EDkWhhOeOpPndQ6IuSl4NmnJg%2Fcq6f8csW8M3Ys%2BMZPFkdxPC4%2FfRM1XC9o76PjpVNBIO%2ByJEELKZedwIDAQAB; lr=1644769628; _Ruby2_session=Q1drcmlhazYvUFZLd0NydnRXUGpoUzArZDlxYWRCcW9sRUx5VDBydWVWRHdGWDZlMnlESURzbldwbFV1L0drbUlKaWt5MXRtaS9iR0ZYZEpPVHQ1N25qRnR1d3FrY0tzQW1qQm9CdTZ3MSs0d2c3MlpuMjRiQWhCOHI1cGNWekZ4cUdJd0ZFcGtpeng3MFlqZjFDUW9RYmpFMU9DeGdGMVZKR1EwMjVhSE9yVHl4VXFtQm9aYVBtNHF5d0pwMjJ1aVlNMUVRUzdnVFZWZ1AxQkY5Q0p6a2RKay9QL05tOWk4cHZiSERtaGRxeTlxTWZnV3Q0cjdwR3RndUtmeUp3QThhMnJaV2dGZjlPUUtjcGRidDhiajRxK2g0RUZTMWNZUDBaeGNCcUVxSDJ1QnZVRlRkWk9tUExJNWN3TDN5T1BQcmhVVGsycStVTzJRaUwvSkk2TnNVZldTOGU3Tm5wQ3RUMy9nazFqbzdrUWtvYzRwQWRpV3dnTVB3YzhodFV2U0FRR3VKdllMY01NZmdOdGtmOEJ4UT09LS1nTXBrYldhQ0pEeWJ3ak9qQjcrTGV3PT0%3D--1439f36a7f9362aee4b5b666747a2d63d72e81bd'
}
response = requests.request("POST", url, headers=headers, data=payload)
stock_info = response.json()['stock_infos']
stock_data(stock_info)

The added block of code is added after the csv file has already been written.
You have other problems as well but that is the most obvious at the moment.
it should be closer to...
...
for info in stock_info:
key = info[0]
for i, sub in enumerate(info[1:], 1):
if sub == key:
print(info[i:])
break
stock_data(stock_info)
Also the added block of code doesn't actually make any changes to the data, it only changes what ends up getting printed. Whatever changes you want made to the file need to be made to stock_info.

python requests not returning json data

I would like to get the json data from for instance https://app.weathercloud.net/d0838117883#current using python requests module.
I tried:
import re
import requests
device='0838117883'
URL='https://app.weathercloud.net'
URL1=URL+'/d'+device
URL2=URL+'/device/stats'
headers={'Content-Type':'text/plain; charset=UTF-8',
'Referer':URL1,
'User-Agent':'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/48.0.2564.82 Chrome/48.0.2564.82 Safari/537.36',
'Accept':'application/json, text/javascript,*/*'}
with requests.Session() as s:
#get html from URL1 in order to get the CSRF token
page = s.get(URL1)
CSRF=re.findall('WEATHERCLOUD_CSRF_TOKEN:"(.*)"},',page.text)[0]
#create parameters for URL2, in order to get the json file
params={'code':device,'WEATHERCLOUD_CSRF_TOKEN':CSRF}
page_stats=requests.get(URL2,params=params,headers=headers)
print(page_stats.url)
print(page_stats) #<Response [200]>
print(page_stats.text) #empty
print(page_stats.json()) #error
But the page_stats is empty.
How can I get the stats data from weathercloud?

Inspecting the page with DevTools, you'll find a useful endpoint:
https://app.weathercloud.net/device/stats
You can "replicate" the original web request made by your browser with requests library:
import requests
cookies = {
'PHPSESSID': '************************',
'WEATHERCLOUD_CSRF_TOKEN':'***********************',
'_ga': '**********',
'_gid': '**********',
'__gads': 'ID=**********',
'WeathercloudCookieAgreed': 'true',
'_gat': '1',
'WEATHERCLOUD_RECENT_ED3C8': '*****************',
}
headers = {
'Connection': 'keep-alive',
'sec-ch-ua': '^\\^Google',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'X-Requested-With': 'XMLHttpRequest',
'sec-ch-ua-mobile': '?0',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36',
'sec-ch-ua-platform': '^\\^Windows^\\^',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Dest': 'empty',
'Referer': 'https://app.weathercloud.net/d0838117883',
'Accept-Language': 'it-IT,it;q=0.9,en-US;q=0.8,en;q=0.7,es;q=0.6',
}
params = (
('code', '0838117883'),
('WEATHERCLOUD_CSRF_TOKEN', '****************'),
)
response = requests.get('https://app.weathercloud.net/device/stats', headers=headers, params=params, cookies=cookies)
# Serializing json
json_object = json.loads(response.text)
json Output:
{'last_update': 1632842172,
'bar_current': [1632842172, 1006.2],
'bar_day_max': [1632794772, 1013.4],
'bar_day_min': [1632845772, 1006.2],
'bar_month_max': [1632220572, 1028],
'bar_month_min': [1632715572, 997.3],
'bar_year_max': [1614418512, 1038.1],
'bar_year_min': [1615434432, 988.1],
'wdir_current': [1632842172, 180],
..............}
That's it.

How can I use Python to get a download link with a password for onedrive

OneDrive is a great tool, but the downside is that for links shared by others there is no way to download them without a graphical interface.
I've recently been working on how to download OneDrive files that people have shared with me from the command line, and I've now worked out how to bulk push download links to Aria2, a download tool, when the shared links don't have passwords.
header = {
'sec-ch-ua-mobile': '?0',
'upgrade-insecure-requests': '1',
'dnt': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 Edg/90.0.818.51',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'service-worker-navigation-preload': 'true',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'navigate',
'sec-fetch-dest': 'iframe',
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
}
def downloadFiles(originalPath, aria2URL, token):
req = requests.session()
req = req.get(originalPath, headers=header)
p = re.search(
'g_listData = {"wpq":"","Templates":{},"ListData":{ "Row" : ([\s\S]*?),"FirstRow"', req.text)
jsonData = json.loads(p.group(1))
redURL = req.url
redsURL = redURL.split("/")
downloadURL = "/".join(redsURL[:-1])+"/download.aspx?UniqueId="
# print(downloadURL)
s2 = parse.urlparse(redURL)
header["referer"] = redURL
header["cookie"] = req.headers["Set-Cookie"]
header["authority"] = s2.netloc
# .replace("-", "%2D")
# print(dd, [cc])
headerStr = ""
for key, value in header.items():
# print(key+':'+str(value))
headerStr += key+':'+str(value)+"\n"
# print(headerStr)
for i in jsonData:
cc = downloadURL+(i["UniqueId"][1:-1].lower())
dd = dict(out=i["FileLeafRef"], header=headerStr)
jsonreq = json.dumps({'jsonrpc': '2.0', 'id': 'qwer',
'method': 'aria2.addUri',
"params": ["token:"+token, [cc], dd]})
c = requests.post(aria2URL, data=jsonreq)
pprint(json.loads(c.text))
However, if the link itself has a password, although it is possible to post a link that verifies the password, it gets stuck in endless redirects, so how do I solve this problem?
The process of post a link to verify a password:
def getFilesHavePwd(originalPath, password):
req = requests.session()
req.cookies.update(header)
r = req.get(originalPath)
p = re.search(
'SideBySideToken" value="(.*?)" />', r.text)
SideBySideToken = p.group(1)
p = re.search(
'id="__VIEWSTATE" value="(.*?)" />', r.text)
__VIEWSTATE = p.group(1)
p = re.search(
'id="__VIEWSTATEGENERATOR" value="(.*?)" />', r.text)
__VIEWSTATEGENERATOR = p.group(1)
p = re.search(
'__EVENTVALIDATION" value="(.*?)" />', r.text)
__EVENTVALIDATION = p.group(1)
s2 = parse.urlparse(originalPath)
redURL = originalPath
redsURL = redURL.split("/")
shareQuery = s2.path.split("/")[-1]
redsURL[-1] = "guestaccess.aspx?"+s2.query+"&share="+shareQuery
pwdURL = "/".join(redsURL)
print(r.headers)
hewHeader = {
'sec-ch-ua-mobile': '?0',
'upgrade-insecure-requests': '1',
'dnt': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 Edg/90.0.818.51',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'content-type': 'application/x-www-form-urlencoded',
"connection": "keep-alive",
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
"host": s2.netloc,
"origin": s2.scheme+"://"+s2.netloc,
"Referer": originalPath,
'sec-ch-ua-mobile': '?0',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
'Cache-Control': 'max-age=0',
}
req.cookies.update(header)
r = req.post(pwdURL, data={
"__EVENTTARGET": "btnSubmitPassword",
"__EVENTARGUMENT": None,
"SideBySideToken": SideBySideToken,
"__VIEWSTATE": __VIEWSTATE,
"__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,
"__VIEWSTATEENCRYPTED": None,
"__EVENTVALIDATION": __EVENTVALIDATION,
"txtPassword": password
}, headers=hewHeader)
print(r.headers, r.text)
A link for test:
https://acgmi-my.sharepoint.com/:f:/g/personal/support_acgmi_club/Elkm2koDXKFEq1onWqnefdwBTqR7wgm0MiNvmWWrurKskQ?e=qotSdz
Password:123456

Unable to scrape "shopee.com.my" top selling products page

I am trying to scrape "shopee.com.my" top selling products with scrape and also tried with requests but failed in getting valid JSON object. my requests code is given below:
import requests as r
import json
data = {
'authority': 'shopee.com.my',
'method': 'GET',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'scheme': 'https',
'accept': '*/*, application/json',
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36',
'x-api-source': 'pc',
'x-requested-with': 'XMLHttpRequest',
'x-shopee-language': 'en',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
}
subcat_url = '/Boys-Fashion-cat.27.2427'
id = subcat_url.split('.')[-1]
data['path'] = f'/api/v2/search_items/?by=sales&limit=50&match_id={id}&newest=0&order=desc&page_type=search&version=2'
data['referer'] = f'https://shopee.com.my{subcat_url}?page=0&sortBy=sales'
url = f'https://shopee.com.my/api/v2/search_items/?by=sales&match_id={id}&newest=0&order=desc&page_type=search&version=2'
req = r.get(url, headers=data)
items = req.json()['items']
print(items)
print(f'Items length: {len(items)}')
here is my scrapy code:
import scrapy
import json
from scrapy import Request
from scrapy.http.cookies import CookieJar
header_data = {'authority': 'shopee.com.my',
'method': 'GET',
'scheme': 'https',
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36',
# 'cookie': 'SPC_U=-; SPC_IA=-1; SPC_EC=-; SPC_F=7jrWAm4XYNNtyVAk83GPknN8NbCMQEIk; REC_T_ID=476673f8-eeb0-11ea-8919-48df374df85c; _gcl_au=1.1.1197882328.1599225148; _med=refer; _fbp=fb.2.1599225150134.114138691; language=en; _ga=GA1.3.1167355736.1599225151; csrftoken=mu9M72KLd73P9QJusB9zFBP6wV3NGg85; _gid=GA1.3.273342972.1603211749; SPC_SI=yxvc89nmqe97ldvpo6wgeybtc8berzyd; welcomePkgShown=true; AMP_TOKEN=%24NOT_FOUND; REC_MD_41_1000027=1603289427_0_50_0_48; SPC_CT_48918e31="1603289273.lUS7x9IuKN5vNbhzibZCOHrIf6vVQmykU/TXxiOii7w="; SPC_CT_57540430="1603289278.FLT3IdzHC32RmEzFxkOi9pI7qhKIs/yq328elYMuwps="; SPC_CT_50ee4e78="1603289299.gvjW32HwgiQGN/4kj2Ac3YFrpqyHVTO8+UjM+uzxy4E="; _dc_gtm_UA-61915055-6=1; SPC_CT_75d7a2b7="1603289557.t5FvxXhnJacZrKkjnIWCUbAgAxAQ3hG5c1tZBzafwc4="; SPC_R_T_ID="n6Ek85JJY1JZATlhgutfB4KB3qrbmFDYX1+udv1EBAPegPE9xuzM8HFeCy1duskY9+DVLJxe4RqaabhyUuojHQG0NI2TqegihbAge+s3k7w="; SPC_T_IV="SGNXqyZ1jtRYpo5kFeKtYg=="; SPC_R_T_IV="SGNXqyZ1jtRYpo5kFeKtYg=="; SPC_T_ID="n6Ek85JJY1JZATlhgutfB4KB3qrbmFDYX1+udv1EBAPegPE9xuzM8HFeCy1duskY9+DVLJxe4RqaabhyUuojHQG0NI2TqegihbAge+s3k7w="',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'x-api-source': 'pc',
'x-requested-with': 'XMLHttpRequest',
'x-shopee-language': 'en',
}
class TestSpider(scrapy.Spider):
name = 'test'
allowed_domains = ['shopee.com', 'shopee.com.my', 'shopee.com.my/api/']
def start_requests(self):
subcat_url = '/Baby-Toddler-Play-cat.27.23785'
id = subcat_url.split('.')[-1]
header_data['path'] = f'/api/v2/search_items/?by=sales&limit=50&match_id={id}&newest=0&order=desc&page_type=search&version=2'
header_data['referer'] = f'https://shopee.com.my{subcat_url}?page=0&sortBy=sales'
url = f'https://shopee.com.my/api/v2/search_items/?by=sales&limit=50&match_id={id}&newest=0&order=desc&page_type=search&version=2'
yield Request(url=url, headers=header_data)
def parse_data(self, response):
try:
jdata = json.loads(response.body)
return None
except Exception as e:
print(f'exception: {e}')
print(response.body)
return None
items = jdata['items']
for item in items:
name = item['name']
image_path = item['image']
absolute_image = f'https://cf.shopee.com.my/file/{image_path}_tn'
print(f'this is absolute image {absolute_image}')
monthly_sold = 'pending'
price = float(item['price'])/100000
total_sold = item['sold']
location = item['shop_location']
stock = item['stock']
print(name)
print(price)
print(total_sold)
print(location)
print(stock)
not using cookies now but also tried with fresh cookies but no response.
Here are some example links where some so them responses always valid JSON object but some links not return any response. see below api and direct browser links:
https://shopee.com.my/Kids-Sports-Outdoor-Play-cat.27.21700?page=0&sortBy=sales
https://shopee.com.my/api/v2/search_items/?by=sales&limit=50&match_id=21700&newest=0&order=desc&page_type=search&version=2
https://shopee.com.my/Bath-Toiletries-cat.27.2422
https://shopee.com.my/api/v2/search_items/?by=sales&limit=50&match_id=2422&newest=0&order=desc&page_type=search&version=2
you can also see API links in network tab:
network tab link image

I think you are missing a required header I send them like this and it worked
from pprint import pprint
import requests
headers = {
'authority': 'shopee.com.my',
'pragma': 'no-cache',
'cache-control': 'no-cache',
'x-shopee-language': 'en',
'x-requested-with': 'XMLHttpRequest',
'if-none-match-': '55b03-c3d70d78b473147beeb6551fa9df8ca0',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36',
'x-api-source': 'pc',
'accept': '*/*',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://shopee.com.my/Kids-Sports-Outdoor-Play-cat.27.21700?page=0&sortBy=sales',
'accept-language': 'es-US,es;q=0.9,en-US;q=0.8,en;q=0.7,es-419;q=0.6',
# 'cookie': '_gcl_au=1.1.1866522785.1603486253; _fbp=fb.2.1603486253254.1114160447; SPC_IA=-1; SPC_EC=-; SPC_U=-; SPC_F=9RO26eJM7IQiFlxki0dAdQCcCsgPwz67; REC_T_ID=71a698d6-1571-11eb-9baf-48df3757c438; SPC_SI=mall.n58BgakbNjCD5RDYlsQJ8EurmBkH5HIY; SPC_CT_c49f0fdc="1603486254.GqWz1BPlfz3MKmUufL3eTwFqgUfdKWcWVf2xiJI7nSk="; SPC_R_T_ID="89vber/2TKnfACAmGbXpxC3BzHc0ajEQMPxgMbAlZnQlgEo7YWmya0sf/KRt1FsoZvaFYKoNDk+Rh9YWLWsNMH324iqgZePbam1q9QpYQlE="; SPC_T_IV="vko6vAtWsyHuqteFHAoPIA=="; SPC_R_T_IV="vko6vAtWsyHuqteFHAoPIA=="; SPC_T_ID="89vber/2TKnfACAmGbXpxC3BzHc0ajEQMPxgMbAlZnQlgEo7YWmya0sf/KRt1FsoZvaFYKoNDk+Rh9YWLWsNMH324iqgZePbam1q9QpYQlE="; AMP_TOKEN=%24NOT_FOUND; _ga=GA1.3.602723004.1603486255; _gid=GA1.3.657631736.1603486255; _dc_gtm_UA-61915055-6=1; language=en',
}
params = (
('by', 'sales'),
('limit', '50'),
('match_id', '21700'),
('newest', '0'),
('order', 'desc'),
('page_type', 'search'),
('version', '2'),
)
response = requests.get('https://shopee.com.my/api/v2/search_items/', headers=headers, params=params)
pprint(response.json())

Categories