Combining multiple sets of data to one JSON file from api calls - python

I need two sets of data from this website:
https://www.nasdaq.com/market-activity/stocks/aapl/institutional-holdings
Which include both the "Active Positions" and "New and Sold Out Positions" tables. The code i have can only provide one piece of data into a JSON:
import requests
import pandas as pd
url = 'https://api.nasdaq.com/api/company/AAPL/institutional-holdings?limit=15&type=TOTAL&sortColumn=marketValue&sortOrder=DESC'
headers = {
'accept': 'application/json, text/plain, */*',
'origin': 'https://www.nasdaq.com',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36'
}
r = requests.get(url, headers=headers)
df = pd.json_normalize(r.json()['data']['newSoldOutPositions']['rows'])
df.to_json('AAPL_institutional_positions.json')
This will give the output of the following (JSON):
{
"positions":{
"0":"New Positions",
"1":"Sold Out Positions"
},
"holders":{
"0":"99",
"1":"90"
},
"shares":{
"0":"37,374,118",
"1":"4,637,465"
}
}
Whereas, for the other table I am scraping, I use this code (All's I have done is change "newSoldOutPositions" to "activePositions"):
import requests
import pandas as pd
url = 'https://api.nasdaq.com/api/company/AAPL/institutional-holdings?limit=15&type=TOTAL&sortColumn=marketValue&sortOrder=DESC'
headers = {
'accept': 'application/json, text/plain, */*',
'origin': 'https://www.nasdaq.com',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36'
}
r = requests.get(url, headers=headers)
df = pd.json_normalize(r.json()['data']['activePositions']['rows'])
df.to_json('AAPL_institutional_positions.json')
Which gives this output (JSON):
{
"positions":{
"0":"Increased Positions",
"1":"Decreased Positions",
"2":"Held Positions",
"3":"Total Institutional Shares"
},
"holders":{
"0":"1,780",
"1":"2,339",
"2":"283",
"3":"4,402"
},
"shares":{
"0":"239,170,203",
"1":"209,017,331",
"2":"8,965,339,255",
"3":"9,413,526,789"
}
}
So my question being, is how can i combine the scraping to grab both sets of data and output them all in one JSON file?
Thanks


If you only want json data, there is no need to use pandas:
import requests
nasdaq_dict = {}
url = 'https://api.nasdaq.com/api/company/AAPL/institutional-holdings?limit=15&type=TOTAL&sortColumn=marketValue&sortOrder=DESC'
headers = {
'accept': 'application/json, text/plain, */*',
'origin': 'https://www.nasdaq.com',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36'
}
r = requests.get(url, headers=headers)
nasdaq_dict['activePositions'] = r.json()['data']['activePositions']['rows']
nasdaq_dict['newSoldOutPositions'] = r.json()['data']['newSoldOutPositions']['rows']
print(nasdaq_dict)
Result in terminal:
{'activePositions': [{'positions': 'Increased Positions', 'holders': '1,795', 'shares': '200,069,709'}, {'positions': 'Decreased Positions', 'holders': '2,314', 'shares': '228,105,026'}, {'positions': 'Held Positions', 'holders': '308', 'shares': '8,976,744,094'}, {'positions': 'Total Institutional Shares', 'holders': '4,417', 'shares': '9,404,918,829'}], 'newSoldOutPositions': [{'positions': 'New Positions', 'holders': '121', 'shares': '55,857,143'}, {'positions': 'Sold Out Positions', 'holders': '73', 'shares': '8,851,038'}]}

Related

Changing layout and adding titles to JSON file with python

I'm trying to extract data from two different api endpoints and create a JSON file with said data. I wish to have titles for each object to distinguish the different data. My code is below:
import requests
import json
headers = {
'accept-language': 'en-US,en;q=0.9',
'origin': 'https://www.nasdaq.com/',
'referer': 'https://www.nasdaq.com/',
'accept': 'application/json, text/plain, */*',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
dataAAPL = requests.get('https://api.nasdaq.com/api/company/AAPL/insider-trades?limit=15&type=ALL&sortColumn=lastDate&sortOrder=DESC',
headers=headers).json()['data']['numberOfSharesTraded']['rows'][3]
dataMSFT = requests.get('https://api.nasdaq.com/api/company/MSFT/insider-trades?limit=15&type=ALL&sortColumn=lastDate&sortOrder=DESC',
headers=headers).json()['data']['numberOfSharesTraded']['rows'][3]
with open('AAPL_insider_piechart.json', 'w') as f:
json.dump(dataAAPL, f, indent=4)
json.dump(dataMSFT, f, indent=4)
And this is the output JSON:
{
"insiderTrade": "Net Activity",
"months3": "(1,317,881)",
"months12": "(1,986,819)"
}
{
"insiderTrade": "Net Activity",
"months3": "185,451",
"months12": "31,944"
}
What I need, is for the JSON to look something like this:
{
"AAPL":[
{
"insiderTrade": "Net Activity",
"months3": "(1,317,881)",
"months12": "(1,986,819)"
}
],
"MSFT":[
{
"insiderTrade": "Net Activity",
"months3": "185,451",
"months12": "31,944"
}
]
}

Just create a dictionary and place the two values in it before dumping it as JSON.
Solution
import requests
import json
headers = {
'accept-language': 'en-US,en;q=0.9',
'origin': 'https://www.nasdaq.com/',
'referer': 'https://www.nasdaq.com/',
'accept': 'application/json, text/plain, */*',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
dataAAPL = requests.get('https://api.nasdaq.com/api/company/AAPL/insider-trades?limit=15&type=ALL&sortColumn=lastDate&sortOrder=DESC',
headers=headers).json()['data']['numberOfSharesTraded']['rows'][3]
dataMSFT = requests.get('https://api.nasdaq.com/api/company/MSFT/insider-trades?limit=15&type=ALL&sortColumn=lastDate&sortOrder=DESC',
headers=headers).json()['data']['numberOfSharesTraded']['rows'][3]
with open('AAPL_insider_piechart.json', 'w') as f:
obj = {
"AAPL": [dataAAPL],
"MSFT": [dataMSFT]
}
json.dump(obj, f, indent=4)

Obtain data of Freight Index in python

I am trying to get the data from this website, https://en.macromicro.me/charts/947/commodity-ccfi-scfi , for China and Shanghai Continerized Freight Index.
I understand that the data is called from an API, how do I find out how the call is made and how do I extract it using python?
I am new in html in general so I have no idea where to start.
I tried,
import requests
url = "https://en.macromicro.me/charts/data/947/commodity-ccfi-scfi"
resp = requests.get(url)
resp = resp.json()
But the response is <Response [404]>
If I change the url to https://en.macromicro.me/charts/data/947/
the response is {'success': 0, 'data': [], 'msg': 'error #644'}

Try the below
import requests
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36',
'Referer': 'https://en.macromicro.me/charts/947/commodity-ccfi-scfi',
'X-Requested-With': 'XMLHttpRequest',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Authorization': 'Bearer 9633cefba71a598adae0fde0b56878fe',
'Cookie': 'PHPSESSID=n74gv10hc8po7mrj491rk4sgo1; _ga=GA1.2.1231997091.1631627585; _gid=GA1.2.1656837390.1631627585; _gat=1; _hjid=c52244fd-b912-4d53-b0e3-3f11f430b51c; _hjFirstSeen=1; _hjAbsoluteSessionInProgress=0'}
r = requests.get('https://en.macromicro.me/charts/data/947', headers=headers)
print(r.json())
output
{'success': 1, 'data': {' ...}

Web scraping - his application is out of date, please click the refresh button on your browser return message

I would like to scrape some data from the following web site: https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract
Steps I would like to automate are:
Choose "Opcinski sud/ZK odjel". For example choose "Zemljišnoknjižni odjel Benkovac".
Choose "Glavna knjiga". For example choose "BENKOVAC"
Enter "Broj kat. čestice:". For example, enter 576/2.
Select "Da" in "Povijesni pregled" (the last row, leave "Broj ZK uloska empty").
Click "Pregledaj" and solve the captcha.
Scrape html that appers.
I have tried to follow above steps using plain requests in python by following network, after opening inspector in the web browser.
There are lots of requests on the page. I will divide my code in several steps:
Start session and make requests that on the start of the page
import requests
import re
import shutil
from twocaptcha import TwoCaptcha
import pandas as pd
import numpy as np
import os
from pathlib import Path
import json
import uuid
# start session
url = 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract'
session = requests.Session()
session.get(url)
jid = session.cookies.get_dict()['JSESSIONID']
# some requests on the start of the page (probabbly redundandt)
headers = {
'Referer': 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36',
}
session.get("https://oss.uredjenazemlja.hr/public/js/libs/modernizr-2.5.3.min.js", headers = headers) #
session.get("https://oss.uredjenazemlja.hr/public/js/libs/jquery-1.7.1.min.js", headers = headers) #
session.get("https://oss.uredjenazemlja.hr/public/js/script.js", headers = headers) # script.json
# no cache json
headers = {
'Cookie': 'ossprivatelang=hr_HR; gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; JSESSIONID=' + jid,
"Connection": "keep-alive",
'Host': 'oss.uredjenazemlja.hr',
'Referer': 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
"sec-ch-ua": '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
"sec-ch-ua-mobile": "?0",
"Sec-Fetch-Dest": "script",
"Sec-Fetch-Mode": "no-cors",
"Sec-Fetch-Site": "same-origin",
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
}
res = session.get('https://oss.uredjenazemlja.hr/public/gwt/hr.ericsson.oss.ui.pia.OssPiaModule.nocache.js', headers = headers)
cache_html = re.findall(r'bc=\'(.*\.cache.html)\',C', res.text)[0]
# cache_html = "1F6C776DEF6D55F56C900B938F84D726.cache.html"
# some more requests on the start of the page (probabbly redundandt)
headers = {
'Referer': 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36',
}
session.get("https://oss.uredjenazemlja.hr/public/gwt/tiny_mce_editor/tiny_mce_src.js", headers = headers) # tiny_mce_src.js
session.get("https://oss.uredjenazemlja.hr/public/gwt/js/common.js", headers = headers)
session.get("https://oss.uredjenazemlja.hr/public/gwt/js/blueimp_tmpl.js", headers = headers) # blueimp_tmpl.js
# cache json
headers = {
"DNT": "1",
'Referer': 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
"sec-ch-ua": '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
'sec-ch-ua-mobile': '?0',
'Sec-Fetch-Dest': 'iframe',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
}
session.get('https://oss.uredjenazemlja.hr/public/gwt/' + cache_html, headers = headers)
Then, I made requests for steps 1 and 2 above:
# commonRPCService opcinski sud 1
headers = {
'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'hr-HR,hr;q=0.9,en-US;q=0.8,en;q=0.7',
'Connection': 'keep-alive',
# 'Content-Length': '166',
'Content-Type': 'text/x-gwt-rpc; charset=UTF-8',
'Cookie': 'gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; ossprivatelang=hr_HR; __utma=79801043.802441445.1616788486.1616788486.1616788486.1; __utmz=79801043.1616788486.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided); x-auto-31=m%3Acollapsed%7Cb%3Atrue; JSESSIONID=' + jid,
"DNT": "1",
'Host': 'oss.uredjenazemlja.hr',
'Origin': 'https://oss.uredjenazemlja.hr',
'Referer': 'https://oss.uredjenazemlja.hr/public/gwt/' + cache_html,
'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/80.0.3987.122 Safari/537.36'
}
payload = '5|0|4|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getMainBook|1|2|3|4|0|'
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
headers = headers,
data=payload
)
print(res.text)
# commonRPCService opcinski sud 2
payload = '5|0|18|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getLrInstitutions|com.extjs.gxt.ui.client.data.BaseModel|hr.ericsson.oss.ui.common.client.core.data.RpcModel/2891266824|dirty|java.lang.Boolean/476441737|new|deleted|resourceCode|java.lang.Integer/3438268394|elementSelected|class|java.lang.String/2004016611|hr.ericsson.jis.domain.admin.Institution|name||1|2|3|4|1|5|6|7|7|8|0|9|-2|10|-2|11|12|0|13|-2|14|15|16|17|15|18|'
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
# print(res.text)
# commonRPCService glavna knjiga 1
payload = '5|0|4|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getMainBook|1|2|3|4|0|'
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
print(res.text)
# commonRPCService glavna knjiga 2
payload = ('5|0|34|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getMainBooks|com.extjs.gxt.ui.client.data.BaseModel|hr.ericsson.oss.ui.common.client.core.data.RpcModel/2891266824|dirty|java.lang.Boolean/476441737|new|deleted|resourceCode|java.lang.Integer/3438268394|elementSelected|cadastralMunicipality|class|java.lang.String/2004016611|hr.ericsson.jis.domain.admin.CadastralMunicipality|hr.ericsson.jis.domain.admin.MainBook|institution|institutionId|parentInstitution|name|Općinski sud u Zadru|hr.ericsson.jis.domain.admin.Institution|institutionType|institutionTypeId|hr.ericsson.jis.domain.admin.InstitutionType|source|superviseInstitutionId|Zemljišnoknjižni odjel Benkovac|place|BENKOVAC|preconditionsRequired||1|2|3|4|1|5|6|10|7|8|0|9|-2|10|-2|11|12|0|13|-2|14|6|1|15|16|17|15|16|18|19|6|13|7|-2|9|-2|20|12|500|21|6|8|7|-2|9|-2|10|-2|20|12|605|11|12|0|13|-2|22|16|23|15|16|24|25|6|7|7|-2|9|-2|10|-2|26|12|14|11|-11|13|-2|15|16|27|28|12|1|10|-2|29|-10|11|-11|13|-2|22|16|30|31|16|32|15|-13|33|-2|22|16|34|').encode("utf-8")
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
Than I solve the captcha:
# some captcha post
payload = ('5|0|4|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|isCaptchaDisabled|1|2|3|4|0|').encode('utf-8')
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
print(res.text)
# get and save captcha
TWO_CAPTCHA_APY_KEY = "myapikey"
solver = TwoCaptcha(TWO_CAPTCHA_APY_KEY)
save_path = 'D:/zkrh/captchas'
p = session.get('https://oss.uredjenazemlja.hr/servlets/kaptcha.jpg?1617088523212',
headers=headers,
stream=True)
captcha_path = os.path.join(Path(save_path), 'captcha' + ".jpg")
with open(captcha_path, 'wb') as out_file:
shutil.copyfileobj(p.raw, out_file)
# solve captcha
result = solver.normal(captcha_path, minLength=5, maxLength=5)
payload = ('5|0|6|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|validateCaptcha|java.lang.String|' +
result['code'] + '|1|2|3|4|1|5|6|').encode('utf-8')
res = requests.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
if res.text.startswith("//OK"):
os.rename(captcha_path, os.path.join(Path(save_path), result['code'] + ".jpg"))
else:
print("Kriva captcha. Rijesi!")
Now, here is the most important request and I can't get the right output from it. It should return lots of numbers where the most important number is one with 7 digits (\d{7}. the should be 1 or more of such numbers). I can use that number in the last step, to get html Here is my try:
payload = ('5|0|40|https://oss.uredjenazemlja.hr/public/gwt/|0EAC9F40996251FDB21FF254E1600E83|hr.ericsson.oss.ui.pia.client.rpc.IOssPublicRPCService|getLrUnitsByMainBookAndParcel|com.extjs.gxt.ui.client.data.BaseModel|java.lang.String|hr.ericsson.oss.ui.common.client.core.data.RpcModel/2891266824|date|java.sql.Date/3996530531|dirty|java.lang.Boolean/476441737|new|cadastralMunicipality|id|java.lang.Integer/3438268394|class|java.lang.String/2004016611|hr.ericsson.jis.domain.admin.CadastralMunicipality|cadastralMunicipalityId|source|creationDate|formatedName|BENKOVAC|userId|cadInstitution|deleted|institutionId|resourceCode|elementSelected|name|Odjel za katastar nekretnina Benkovac|hr.ericsson.jis.domain.admin.Institution|institution|Zemljišnoknjižni odjel Benkovac|place|sidMainBook|java.lang.Long/4227064769|hr.ericsson.jis.domain.admin.MainBook|status|576/2|1|2|3|4|2|5|6|7|18|8|9|115|10|21|10|11|0|12|-3|13|7|3|14|15|98|16|17|18|19|-5|20|15|1|21|9|116|0|1|22|17|23|24|15|-9999|25|7|8|10|-3|12|-3|26|-3|27|15|117|28|15|0|29|-3|30|17|31|16|17|32|33|7|9|10|-3|12|-3|26|-3|27|15|500|28|-13|29|-3|30|17|34|35|-9|16|-15|26|-3|28|15|0|29|-3|30|-9|36|37|4730091|0|14|15|30857|16|17|38|39|-19|40|').encode('utf-8')
res = session.post(
'https://oss.uredjenazemlja.hr/rpc/commonRPCService',
data=payload,
headers=headers
)
print(res.text)
It returns:
"//EX[2,1,["com.google.gwt.user.client.rpc.IncompatibleRemoteServiceException/3936916533","This application is out of date, please click the refresh button on your browser. ( Blocked attempt to access interface 'hr.ericsson.oss.ui.pia.client.rpc.IOssPublicRPCService', which is not implemented by 'hr.ericsson.oss.ui.common.server.core.rpc.CommonRPCService'; this is either misconfiguration or a hack attempt )"],0,5]"
instead of numbers as I explained before.
Then, in the last step, I should use 7 digit number as lrUnitNumber parameter
# Publicreportservlet
headers = {
'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',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'hr-HR,hr;q=0.9,en-US;q=0.8,en;q=0.7',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Content-Length': '169',
'Content-Type': 'application/x-www-form-urlencoded',
'Cookie': 'ossprivatelang=hr_HR; gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; JSESSIONID=' + jid,
'Host': 'oss.uredjenazemlja.hr',
'Origin': 'https://oss.uredjenazemlja.hr',
'Referer': 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
'Sec-Fetch-Dest': 'iframe',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
}
dataFrom = {
'pia': 1,
'report_type_id': 4,
'report_type_name': 'bzp_izvadak_oss',
'source': 1,
'institutionID': 500,
'mainBookId': 30857,
'lrUnitNumber': 5509665,
'lrunitID': 5799992,
'status': '0,1',
'footer': '',
'export_type': 'html'
}
res = session.post(
'https://oss.uredjenazemlja.hr/servlets/PublicReportServlet',
data=dataFrom,
headers=headers
)
res
I am providing the R ode too. Maybe someone with R and web scraping knowledge can help:
library(httr)
library(rvest)
library(stringr)
library(reticulate)
twocaptcha <- reticulate::import("twocaptcha")
# captcha python library
TWO_CAPTCHA_APY_KEY = ".."
solver = twocaptcha$TwoCaptcha(TWO_CAPTCHA_APY_KEY)
#
url = 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract'
session = GET(url)
jid <- cookies(session)$value
headers_cache = c(
'Referer'= 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
'User-Agent'= 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
)
session <- rvest:::request_GET(content(session), 'https://oss.uredjenazemlja.hr/public/gwt/hr.ericsson.oss.ui.pia.OssPiaModule.nocache.js',
add_headers(headers_cache))
cache_html <- str_extract(session$response, "bc=\\'(.*\\.cache.html)\\',C")
cache_html <- gsub(".*=\\'|\\'.C", "", cache_html)
headers_cache = c(
'Referer'= 'https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract',
'User-Agent'= 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
)
session <- rvest:::request_GET(session, paste0('https://oss.uredjenazemlja.hr/public/gwt/', cache_html), add_headers(headers_cache))
# meta
commonRPCServiceUrl <- "https://oss.uredjenazemlja.hr/rpc/commonRPCService"
headers = c(
'Accept'= '*/*',
'Accept-Encoding'= 'gzip, deflate, br',
'Accept-Language'= 'hr-HR,hr;q=0.9,en-US;q=0.8,en;q=0.7',
'Connection'= 'keep-alive',
# 'Content-Length'= '166',
'Content-Type'= 'text/x-gwt-rpc; charset=UTF-8',
'Cookie'= paste0('gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; ossprivatelang=hr_HR; x-auto-31=m%3Acollapsed%7Cb%3Atrue; JSESSIONID=', jid),
'Host'= 'oss.uredjenazemlja.hr',
'Origin'= 'https://oss.uredjenazemlja.hr',
'Referer'= paste0('https://oss.uredjenazemlja.hr/public/gwt/', cache_html),
'Sec-Fetch-Dest'= 'empty',
'Sec-Fetch-Mode'= 'cors',
'Sec-Fetch-Site'= 'same-origin',
'User-Agent'= 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
)
payload <- "5|0|4|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getMainBook|1|2|3|4|0|"
session <- rvest:::request_POST(session, commonRPCServiceUrl, body = payload, add_headers(headers))
session$response$content
readBin(session$response$content, character(), endian = "little")
payload <- "5|0|22|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|getMainBooks|com.extjs.gxt.ui.client.data.BaseModel|hr.ericsson.oss.ui.common.client.core.data.RpcModel/2891266824|dirty|java.lang.Boolean/476441737|new|deleted|resourceCode|java.lang.Integer/3438268394|elementSelected|cadastralMunicipality|class|java.lang.String/2004016611|hr.ericsson.jis.domain.admin.CadastralMunicipality|hr.ericsson.jis.domain.admin.MainBook|institution|preconditionsRequired|name|VELIKA GORICA|1|2|3|4|1|5|6|10|7|8|0|9|-2|10|-2|11|12|0|13|-2|14|6|1|15|16|17|15|16|18|19|0|20|-2|21|16|22|"
session <- rvest:::request_POST(session, commonRPCServiceUrl, body = payload, add_headers(headers))
session$response$content
readBin(session$response$content, character(), endian = "little")
# captcha
payload <- "5|0|4|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|isCaptchaDisabled|1|2|3|4|0|"
session <- rvest:::request_POST(session, commonRPCServiceUrl, body = payload, add_headers(headers))
session$response$content
readBin(session$response$content, character(), endian = "little")
headers_captcha <- c(
"Accept"= "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
"Accept-Encoding"= "gzip, deflate, br",
"Accept-Language"=" hr-HR,hr;q=0.9,en-US;q=0.8,en;q=0.7",
"Connection"= "keep-alive",
"Cookie"= paste0("gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; ossprivatelang=hr_HR; x-auto-31=m%3Acollapsed%7Cb%3Atrue; JSESSIONID=", jid),
"DNT"= "1",
"Host"= "oss.uredjenazemlja.hr",
"Referer"= "https://oss.uredjenazemlja.hr/public/lrServices.jsp?action=publicLdbExtract",
"sec-ch-ua"= '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
"sec-ch-ua-mobile"= "?0",
"Sec-Fetch-Dest"= "image",
"Sec-Fetch-Mode"= "no-cors",
"Sec-Fetch-Site"= "same-origin",
"User-Agent"= "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36"
)
captcha <- GET("https://oss.uredjenazemlja.hr/servlets/kaptcha.jpg?1617286122160", add_headers(headers_captcha))
# session <- rvest:::request_GET(session, "https://oss.uredjenazemlja.hr/servlets/kaptcha.jpg?1617286122160", add_headers(headers_captcha))
captcha$content
captcha$response$content
writeBin(captcha$content, "D:/zkrh/captchas/test.jpg")
result = solver$normal("D:/zkrh/captchas/test.jpg", minLength=5, maxLength=5)
payload <- paste0("5|0|6|https://oss.uredjenazemlja.hr/public/gwt/|957F3F03E95E97ABBDE314DFFCCEF4BC|hr.ericsson.oss.ui.common.client.core.rpc.ICommonRPCService|validateCaptcha|java.lang.String|",
result$code, "|1|2|3|4|1|5|6|")
session <- rvest:::request_POST(session, commonRPCServiceUrl, body = payload, add_headers(headers))
session$response$content
readBin(p$response$content, character(), endian = "little")
# ID!!!!!!
headers = c(
'Accept'= '*/*',
'Accept-Encoding'= 'gzip, deflate, br',
'Accept-Language'= 'hr-HR,hr;q=0.9,en-US;q=0.8,en;q=0.7',
'Connection'= 'keep-alive',
# 'Content-Length'= '166',
'Content-Type'= 'text/x-gwt-rpc; charset=UTF-8',
'Cookie'= paste0('gxtTheme=m%3Aid%7Cs%3Agray%2Cfile%7Cs%3Axtheme-gray.css; ossprivatelang=hr_HR; x-auto-31=m%3Acollapsed%7Cb%3Atrue; JSESSIONID=', jid),
'DNT' = '1',
'Host'= 'oss.uredjenazemlja.hr',
'Origin'= 'https://oss.uredjenazemlja.hr',
'Referer'= paste0('https://oss.uredjenazemlja.hr/public/gwt/', cache_html),
'sec-ch-ua' = '"Google Chrome";v="89", "Chromium";v="89", ";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/80.0.3987.122 Safari/537.36'
)
payload <- paste0("5|0|40|https://oss.uredjenazemlja.hr/public/gwt/|0EAC9F40996251FDB21FF254E1600E83|hr.ericsson.oss.ui.pia.client.rpc.IOssPublicRPCService|getLrUnitByMainBook|com.extjs.gxt.ui.client.data.BaseModel|java.lang.String|hr.ericsson.oss.ui.common.client.core.data.RpcModel/2891266824|date|java.sql.Date/3996530531|dirty|java.lang.Boolean/476441737|new|cadastralMunicipality|id|java.lang.Integer/3438268394|class|java.lang.String/2004016611|hr.ericsson.jis.domain.admin.CadastralMunicipality|cadastralMunicipalityId|source|creationDate|formatedName|VELIKA GORICA|userId|cadInstitution|deleted|institutionId|resourceCode|elementSelected|name|Odjel za katastar nekretnina Velika Gorica|hr.ericsson.jis.domain.admin.Institution|institution|Zemljišnoknjižni odjel Velika Gorica|place|sidMainBook|java.lang.Long/4227064769|hr.ericsson.jis.domain.admin.MainBook|status|1|1|2|3|4|2|5|6|7|18|8|9|114|1|21|10|11|0|12|-3|13|7|3|14|15|102844|16|17|18|19|-5|20|15|1|21|9|116|0|1|22|17|23|24|15|-20|25|7|8|10|-3|12|-3|26|-3|27|15|32|28|15|0|29|-3|30|17|31|16|17|32|33|7|9|10|-3|12|-3|26|-3|27|15|277|28|-13|29|-3|30|17|34|35|-9|16|-15|26|-3|28|-7|29|-3|30|-9|36|37|286610893|17179869184|14|15|21921|16|17|38|39|15|0|40|")
# Encoding(payload) <- "UTF-8"
# payload <- RCurl::curlEscape(payload)
session <- rvest:::request_POST(session, commonRPCServiceUrl, body = payload, add_headers(headers))
session$response$content
readBin(session$response$content, character())

I have found the error. The problem was in wrong url argument in one request.

You should really look into selenium and beautifulsoup4 to automate this - it's like requests on steroids.
see an example on my github: https://github.com/stevenhurwitt/reliant-scrape/blob/master/reliant_scrape.py

Python Requests AJAX Response Different from Browser Due to Cookie Handling

My request:
# python 3.7.3
import requests
from requests import Session
session = Session()
session.head('https://www.basspro.com/shop/en/blazer-brass-handgun-ammo')
cookies = requests.utils.cookiejar_from_dict(requests.utils.dict_from_cookiejar(session.cookies))
response = session.post(
url='https://www.basspro.com/shop/BPSGetInventoryStatusByIDView',
data={
'productId': '3074457345616736172',
'itemId': '3074457345616736949',
'isGunFlag': 'false',
},
cookies=cookies,
headers={
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'content-length': '72',
'content-type': 'application/x-www-form-urlencoded',
'origin': 'https://www.basspro.com',
'referer': 'https://www.basspro.com/shop/en/blazer-brass-handgun-ammo',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.92 Safari/537.36 Vivaldi/2.9.1705.38',
'x-requested-with': 'XMLHttpRequest',
},
)
print(response.text)
Output:
<input type="hidden" class="relativeToAbsolute" value="true" />
/*
{
"onlineInventory": {
"status": "Status Not Available",
"image": "widget_product_info/outofstock_icon.svg",
"altText": "Status Not Available",
"isDropShip": false,
"availableDate":""
},
"inStoreInventory": {
"stores": [],
"checkStoreText": "Check Store Availability",
"isInStoreInventory": true,
"isPickupInventory": false
}
}
*/
My output when inspecting and running the same AJAX request via browser:
/*
{
"onlineInventory": {
"status": "Backordered",
"image": "widget_product_info/backordered_icon.svg",
"altText": "Backordered",
"isDropShip": false,
"quantity": 0,
"availableDate":"May 1-8"
},
"inStoreInventory": {
"stores": [{
id: '715839555',
name: '83',
gunRestricted: 'false',
dsName: 'TX - Round Rock',
status: 'Unavailable',
statusText: 'Out of Stock',
image: 'widget_product_info/outofstock_icon.svg',
altText: 'Out of Stock',
availableDate: '',
availableQuantity: '',
availableQuantityDisplay: 'false',
cityState: 'Round Rock, TX',
ISPavailableDate: '',
ISPavailableQuantity: '',
pickupTime: 'by 2:00pm',
offerISPOnBPS: 'Yes',
offerISPOnCAB: 'No'}],
"checkStoreText": "Change Store",
"isInStoreInventory": true,
"isPickupInventory": true
}
}
*/
I tried assigning cookies this way as well:
url = "https://www.basspro.com/shop/en/blazer-brass-handgun-ammo"
r = requests.get(url)
cookies = r.cookies
# fails to pass the right cookie
If I instead copy the cookie verbatim from an inspected GET request at https://www.basspro.com/shop/en/blazer-brass-handgun-ammo and put that into the POST headers, it works. How do I get cookies to work properly programatically?
EDIT:
Here's my attempt at just using Session() for cookies:
# python 3.7.3
import requests
from requests import Session
session = Session()
session.get("https://www.basspro.com/shop/en/blazer-brass-handgun-ammo")
# session.head('https://www.basspro.com/shop/en/blazer-brass-handgun-ammo')
response = session.post(
url='https://www.basspro.com/shop/BPSGetInventoryStatusByIDView',
data={
'productId': '3074457345616736172',
'itemId': '3074457345616736949',
'isGunFlag': 'false',
},
headers={
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'content-length': '72',
'content-type': 'application/x-www-form-urlencoded',
'origin': 'https://www.basspro.com',
'referer': 'https://www.basspro.com/shop/en/blazer-brass-handgun-ammo',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.92 Safari/537.36 Vivaldi/2.9.1705.38',
'x-requested-with': 'XMLHttpRequest',
},
)
print(response.text)
I get the same result as before ("status": "Status Not Available", etc.)
Here's my attempt at the second solution:
# python 3.7.3
import requests
from requests import Session
url = "https://www.basspro.com/shop/en/blazer-brass-handgun-ammo"
r = requests.get(url)
cookies = r.cookies # the type is RequestsCookieJar
response = requests.post(
url='https://www.basspro.com/shop/BPSGetInventoryStatusByIDView',
data={
'productId': '3074457345616736172',
'itemId': '3074457345616736949',
'isGunFlag': 'false',
},
cookies=cookies,
headers={
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'content-length': '72',
'content-type': 'application/x-www-form-urlencoded',
'origin': 'https://www.basspro.com',
'referer': 'https://www.basspro.com/shop/en/blazer-brass-handgun-ammo',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.92 Safari/537.36 Vivaldi/2.9.1705.38',
'x-requested-with': 'XMLHttpRequest',
},
)
print(response.text)
Again, I get the same result as before. What am I doing wrong?

can you try like this
session = Session()
session.get("https://www.basspro.com/shop/en/blazer-brass-handgun-ammo")
Then all the following calls with
session.xxx
donot use cookies parameter in it
another way I have tested,
cookies = r.cookies # the type is RequestsCookieJar
requests.post(.... cookies=cookies...)
at last ,I tested this works:
Please compare carefully
from requests import Session
session = Session()
agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'
r1 = session.get("https://www.basspro.com/shop/en/blazer-brass-handgun-ammo",headers={'user-agent': agent})
response = session.post(
url='https://www.basspro.com/shop/BPSGetOnlineInventoryStatusByIDView',
data={
'productId': '3074457345616736172',
'catalogId': '3074457345616676768',
'storeId': '715838534',
'langId':-1
},
headers={
'user-agent': agent,
'x-requested-with': 'XMLHttpRequest',
},
cookies=r1.cookies
)
print(response.text)

How to write table format to an Excel sheet?

Here is my Python code:
import requests
url = 'https://www1.nseindia.com/live_market/dynaContent/live_watch/stock_watch/juniorNiftyStockWatch.json'
headers = {
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0, no-cache, no-store',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.0.2990 Safari/537.36',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,hi;q=0.8'
}
cookie_dict = {
'bm_sv': 'FE5D5202FA442377EAE6BE578E5AE53D~TmgiDfrRzUs3GLDNWdi+VYOGUgD/J5uggMUSrRYzOob13kW5hAIyKjXHPWK42UDCM69u2LxxjUmIZ3uo/6orCmkSTim/QNEqHDMaqyU+lnjwtT3j4bI7rpt2OfhdZ/wPYtAQPaG7IJQj8fFUKxNm0EtMj/ZHW8jDRzOvy0JfZhk='
}
session = requests.session()
for cookie in `cookie_dict`:
session.cookies.set(cookie, cookie_dict[cookie])
json = session.get(url, headers = headers).json()
print(json)
Here is the sample output for 2 stocks:
{
"declines":18,
"data":[
{
"symbol":"IDEA",
"open":"4.25",
"high":"4.80",
"low":"4.20",
"ltP":"4.55",
"ptsC":"0.35",
"per":"8.33",
"trdVol":"9,245.45",
"trdVolM":"924.54",
"ntP":"420.67",
"mVal":"4.21",
"wkhi":"15.00",
"wklo":"2.40",
"wkhicm_adj":"183.70",
"wklocm_adj":"125.10",
"xDt":"31-DEC-2999",
"cAct":"-",
"previousClose":"4.20",
"dayEndClose":"4.6",
"iislPtsChange":"0.40",
"iislPercChange":"9.52",
"yPC":"-68.18",
"mPC":"42.19"
},
{
"symbol":"MOTHERSUMI",
"open":"78.50",
"high":"85.00",
"low":"78.10",
"ltP":"80.60",
"ptsC":"3.60",
"per":"4.68",
"trdVol":"547.02",
"trdVolM":"54.70",
"ntP":"450.85",
"mVal":"4.51",
"wkhi":"151.00",
"wklo":"48.65",
"wkhicm_adj":"450.70",
"wklocm_adj":"178.25",
"xDt":"12-MAR-2020",
"cAct":"INTERIM DIVIDEND - RS 1.50 PER SHARE",
"previousClose":"77.00",
"dayEndClose":"80.45",
"iislPtsChange":"3.45",
"iislPercChange":"4.48",
"yPC":"-37.54",
"mPC":"43.42"
}
]
}
How to write this required table format in an Excel sheet while continuously fetching data with a time interval and setting a running time period for the program.
No, symbol, open, high, low, ltp, ptsc, per, trdvol, trdvolm, ntp, mval', wkhi, wklo, wkhicm_adj

Categories

Resources