I know you can loop through page numbers in a URL but is it possible loop through pages in a Payload? I would guess you need beautiful soup? At the end of the Payload, there is this code.
page=1&start=0&limit=250
Currently, I am just getting page 1 with 250 lines. I need to loop through the code and retrieve page=2&start=251&limit=250 and the subsequent 11 pages. Could anyone show me how to do this?
Working Code for first 250 Lines
import requests
import pandas as pd
def stock_data(stock_info):
data = pd.DataFrame(stock_info)
data = data.iloc[:, 4:]
data.to_csv("data.csv", index=False)
url = "https://www.stockrover.com/stock_infos/grid?_dc=1644876887410"
payload = "state=%7B%22sortInfo%22%3A%7B%7D%2C%22columns%22%3A%5B76%2C77%2C50%2C80%2C547%2C13%2C21%2C771%5D%2C%22view%22%3A313%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_42%22%2C%22cIsFolder%22%3Afalse%2C%22gridSelection%22%3A%22ANDE%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%22ANDE%22%5D%2C%22lastQuantNode%22%3A%5B%22s_42%22%2C%22s_42%22%5D%2C%22includeQuotesInTable%22%3Afalse%2C%22includeAllQuotesLastValue%22%3Afalse%2C%22markets%22%3A%7B%22panel%22%3A%22summary%22%7D%2C%22researchPanel%22%3A%22comparisonPanel%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%22ANDE%22%5D%2C%22lastSelectionScreeners%22%3A%22s_42%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_42%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%3A1644837064%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': 'fAeVScD26lby5MQf5YFI5p3snudo3E+rw0TL0h1W3j/vcjsIMvgxAF5Z9DkMjjCU4trT/b4EV0VCCPvmms5VIw==',
'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/all/313/s_42/ANDE',
'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=1644876886; _Ruby2_session=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%3D--b963330daa985315420ea5893f1cfa3e3a54c9d5; _Ruby2_session=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--a126f3bcc5b8af0a5a824e6b674d55f1fe9ee12e; lr=1644876939'
}
for page in range(3):
pld = payload.format(page+1, page*250, 250)
response = requests.request("POST", url, headers=headers, data=pld)
stock_info = response.json()['stock_infos']
stock_data(stock_info)
Here's how you do it in a loop. This works; I've tried it here.
for page in range(3):
pld = payload.format(page+1, page*250, 250)
response = requests.request("POST", url, headers=headers, data=pld)
stock_info = response.json()['stock_infos']
stock_data(stock_info)
You will, of course, need to modify your code so that stock_data doesn't overwrite the CSV file every time. You can either append to one big dataframe, or append to the CSV file.
Related
I am trying to scrape multiple pages with json but they will provide me error
import requests
import json
import pandas as pd
headers = {
'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'Connection': 'keep-alive',
'Origin': 'https://www.nationalhardwareshow.com',
'Referer': 'https://www.nationalhardwareshow.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
'accept': 'application/json',
'content-type': 'application/x-www-form-urlencoded',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
}
params = {
'x-algolia-agent': 'Algolia for vanilla JavaScript 3.27.1',
'x-algolia-application-id': 'XD0U5M6Y4R',
'x-algolia-api-key': 'd5cd7d4ec26134ff4a34d736a7f9ad47',
}
for i in range(0,4):
data = '{"params":"query=&page={i}&facetFilters=&optionalFilters=%5B%5D"}'
resp = requests.post('https://xd0u5m6y4r-dsn.algolia.net/1/indexes/event-edition-eve-e6b1ae25-5b9f-457b-83b3-335667332366_en-us/query', params=params, headers=headers, data=data).json()
req_json=resp
df = pd.DataFrame(req_json['hits'])
f = pd.DataFrame(df[['name','representedBrands','description']])
print(f)
the error :
Traceback (most recent call last):
File "e:\ScriptScraping\Extract data from json\uk.py", line 31, in <module>
df = pd.DataFrame(req_json['hits']) KeyError: 'hits'
Try to concatenate the variable i with data parameter
import requests
import json
import pandas as pd
headers = {
'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'Connection': 'keep-alive',
'Origin': 'https://www.nationalhardwareshow.com',
'Referer': 'https://www.nationalhardwareshow.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
'accept': 'application/json',
'content-type': 'application/x-www-form-urlencoded',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"'
}
params = {
'x-algolia-agent': 'Algolia for vanilla JavaScript 3.27.1',
'x-algolia-application-id': 'XD0U5M6Y4R',
'x-algolia-api-key': 'd5cd7d4ec26134ff4a34d736a7f9ad47'
}
lst=[]
for i in range(0,4):
data = '{"params":"query=&page='+str(i)+'&facetFilters=&optionalFilters=%5B%5D"}'
resp = requests.post('https://xd0u5m6y4r-dsn.algolia.net/1/indexes/event-edition-eve-e6b1ae25-5b9f-457b-83b3-335667332366_en-us/query', params=params, headers=headers, data=data).json()
req_json=resp
df = pd.DataFrame(req_json['hits'])
f = pd.DataFrame(df[['name','representedBrands','description']])
lst.append(f)
#print(f)
d=pd.concat(lst)
print(d)
It is returning status_code 400 as the request is bad. You are sending wrongly formatted data. Change:
data = '{"params":"query=&page={i}&facetFilters=&optionalFilters=%5B%5D"}'
To
data = '{"params":"query=&page='+str(i)+'&facetFilters=&optionalFilters=%5B%5D"}'
For it to work. Hope I could help.
I am having trouble reading data from a url with BeautifulSoup
This is my code:
url1 = "https://www.barstoolsportsbook.com/events/1018282280"
from bs4 import BeautifulSoup
import requests
headers = {
'User-agent':
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}
html = requests.get(url1, headers=headers)
soup = BeautifulSoup(html.text, 'lxml')
data = soup.findAll('div',attrs={"class":"section"})
print(data)
#for x in data:
# print(x.find('p').text)
When I print(data) I am returned []. What could be the reason for this? I would like to avoid using selenium for this task if possible.
This is the HTML for what I'm trying to grab
<div data-v-50e01018="" data-v-2a52296d="" class="section"><p data-v-5f665d29="" data-v-50e01018="" class="header strongbody2">HOT TIPS</p><p data-v-5f665d29="" data-v-50e01018="" class="tip body2"> The Mets have led after 3 innings in seven of their last nine night games against NL East Division opponents that held a losing record. </p><p data-v-5f665d29="" data-v-50e01018="" class="tip body2"> The 'Inning 1 UNDER 0.5 runs' market has hit in each of the Marlins' last nine games against NL East opponents. </p></div>
You can likely get what you want with this request:
import requests
headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:103.0) Gecko/20100101 Firefox/103.0',
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'en-US,en;q=0.5',
'Authorization': 'Basic MTI2OWJlMjItNDI2My01MTI1LWJlNzMtMDZmMjlmMmZjNWM3Omk5Zm9jajRJQkZwMUJjVUc0NGt2S2ZpWEpremVKZVpZ',
'Origin': 'https://www.barstoolsportsbook.com',
'DNT': '1',
'Connection': 'keep-alive',
'Referer': 'https://www.barstoolsportsbook.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
}
response = requests.get('https://api.isportgenius.com.au/preview/1018282280', headers=headers)
response.json()
You should browse the network tab to see where the rest of the data is coming from, or use a webdriver.
import requests
url = "https://baroul-timis.ro/get-av-data?param=toti-avocatii"
payload={}
headers = {
'Accept': 'text/html, */*; q=0.01',
'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Cookie': '_csrf-frontend=ccc4c9069d6ad3816ea693a980ecbebda2770e9448ffe9fed17cdf397a5e2851a%3A2%3A%7Bi%3A0%3Bs%3A14%3A%22_csrf-frontend%22%3Bi%3A1%3Bs%3A32%3A%22J3N0AJG6xybnGl91dfrlt-qMOk3hfbQ6%22%3B%7D',
'Pragma': 'no-cache',
'Referer': 'https://baroul-timis.ro/tabloul-avocatilor/',
'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/102.0.0.0 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="102", "Google Chrome";v="102"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"'
}
resp= requests.request("GET", url, headers=headers, data=payload).json()
sample=resp['data']
for test in sample:
product=test['actions']
print(product)
they give me these url:
<i class="fas fa-address-book" aria-hidden="true"></i>
But I want to these only and also I want to scrape multiple pages but the link of all the pages is same :
/tabloul-avocatilor/avocat/av-felicia-petre
To get all 948 names and links you can use next example:
import requests
from bs4 import BeautifulSoup
url = "https://baroul-timis.ro/get-av-data?param=toti-avocatii"
data = requests.get(url).json()
for i, d in enumerate(data["data"], 1):
first_name = d["firstname"]
last_name = BeautifulSoup(d["lastname"], "html.parser").text
link = BeautifulSoup(d["actions"], "html.parser").a["href"]
print(
"{:<3} {:<30} {:<30} {}".format(
i, first_name[:29], last_name[:29], link
)
)
Prints:
...
943 Adela-Ioana FRUNZĂ /tabloul-avocatilor/avocat/av-adela-frunza
944 Marina GLIGOR-VOLSCHI /tabloul-avocatilor/avocat/av-marina-gligor-volschi
945 Denis-Alexandru TOTH /tabloul-avocatilor/avocat/av-denis-toth
946 Raluca-Roxana ȘURIANU /tabloul-avocatilor/avocat/av-raluca-surianu
947 Alexandra-Bianka CIOBANU /tabloul-avocatilor/avocat/av-alexandra-ciobanu
948 Alexandra-Oana OLARIU /tabloul-avocatilor/avocat/av-alexandra-olariu
I am trying to download a CSV file generated from a report at This website.
Below is the request I am trying to replicate.
Example of API i am trying to call
I copy the cURL and parse it and get the following format for the request:
import requests
cookies = {
'_ga': 'GA1.2.938840467.1566745600',
'terminal': '174224916994986694513353793024390053397',
'__utmc': '1',
'request_timing~11947199': '2~2237~74~91~2402',
'_gid': 'GA1.2.89702438.1657551717',
'cf_clearance': 'RDmwUSB_b6JmRSJpvrM76reZifV_m6cHjCJ0kmUkAS8-1657566551-0-250',
'GSG_SESSION_ID': '322919708739472562779456661040511933493',
'is_session_valid': '1',
'plack_session': '27e03cd7d13a440955626dbc574adef85a619f88',
'__utma': '1.938840467.1566745600.1657299681.1657567143.4',
'__utmz': '1.1657567143.4.4.utmcsr=leetc.com|utmccn=(referral)|utmcmd=referral|utmcct=/',
'__utmt': '1',
'session_id': '53da3a29-e3d5-4dd4-96c3-7562a0fb7715',
'_gat': '1',
'request_id~1513632513': '6441F026-014E-11ED-9669-AEADB5E8FA7B',
'__utmb': '1.5.9.1657567169673',
'request_timing~1513632513': '1~4217~79~105~4401',
}
headers = {
'authority': 'lee.county-taxes.com',
'accept': 'application/xml, text/xml, */*; q=0.01',
'accept-language': 'en-US,en;q=0.9',
'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
# Requests sorts cookies= alphabetically
# 'cookie': '_ga=GA1.2.938840467.1566745600; terminal=174224916994986694513353793024390053397; __utmc=1; request_timing~11947199=2~2237~74~91~2402; _gid=GA1.2.89702438.1657551717; cf_clearance=RDmwUSB_b6JmRSJpvrM76reZifV_m6cHjCJ0kmUkAS8-1657566551-0-250; GSG_SESSION_ID=322919708739472562779456661040511933493; is_session_valid=1; plack_session=27e03cd7d13a440955626dbc574adef85a619f88; __utma=1.938840467.1566745600.1657299681.1657567143.4; __utmz=1.1657567143.4.4.utmcsr=leetc.com|utmccn=(referral)|utmcmd=referral|utmcct=/; __utmt=1; session_id=53da3a29-e3d5-4dd4-96c3-7562a0fb7715; _gat=1; request_id~1513632513=6441F026-014E-11ED-9669-AEADB5E8FA7B; __utmb=1.5.9.1657567169673; request_timing~1513632513=1~4217~79~105~4401',
'origin': 'https://lee.county-taxes.com',
'referer': 'https://lee.county-taxes.com/public/reports/real_estate',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'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/103.0.0.0 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
}
data = 'base_url=public%2Freports%2Freal_estate&parent_request_id=5955C82C-014E-11ED-A791-8C0D896639A2&report_search=cert_status%09%2F%7C%2F%09tax_year%09%3E2014%09roll_year%09*%09cert_sale_date%09%2F%7C%2F%09exemption%09%2F%7C%2F%09deed_status%09%2F%7C%2F%09standard_flag%09%2F%7C%2F%09&report_search_current_user_inputs=&session_id=322919708739472562779456661040511933493&app_url=%2Ftcb%2Fapp&page_url=public%2Freports%2Freal_estate&report_name=Certificate+Information+by+Year&selected_report=624&filetype=csv&delimiter=comma"ing=on&pdf_report_title=Certificate+Information+by+Year+Report+(Certificate+Search)&add_run_by_to_header=on&paper_size=letter&page_orientation=portrait&page_break=auto&break_selector=tax_year&shade_alternate_rows=on&pdf_report_description=&report_download_email_address=&report_took_too_long_download_email=&displayed_columns=certificate_number%7Ccert_status%7Ctax_year%7Croll_year%7Caccount_number%7Csitus_address%7Ccert_sale_date%7Cissued_date%7Cpurchased_date%7Ccertificate_rate%7Cinterest_start_date%7Cface_amount%7Credeemed_date%7Credemption_amount_paid%7Ctransferred_date%7Cexemption%7Cdeed_status%7Cbidder_number%7Ccertificate_buyer%7Cstandard_flag&hide_results=&sort_by_displayed=&hide_public=&display_name=¤t_view=certs¤t_display=data&select_view=certs&last_sort_col=1&sbgb_boundary=2&search_order_column1=tax_year&search_order_column2=&select_display=data&search_order_direction1=desc&report_search_dummy=&report_search_dummy=%2F%7C%2F&report_search_dummy=%3E2014&report_search_dummy=&report_search_dummy=&report_search_dummy=%2F%7C%2F&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=&report_search_dummy=%2F%7C%2F&report_search_dummy=%2F%7C%2F&report_search_dummy=&report_search_dummy=&report_search_dummy=%2F%7C%2F&rows_per_page=50&go_to_report_page=&report_page=1&backend=warehouse&print_cover_page=0&download_now=browser&ajax_request=0.4428397794570913&cookie_id=2025887579'
response = requests.post('https://lee.county-taxes.com/tcb/app/public/reports/real_estate/download', cookies=cookies, headers=headers, data=data)
Unfortunately when I run this code I get the following output in response.content:
b'<ajax-response><response type=\'element_errors\'></response> <response type="element" id="message_container" class=""> </response> <response type="element" id="report_download_util"><![CDATA[ ]]></response> <response type="javascript"><![CDATA[\n file_download(d_location() + \'/download_pending_report?pending_report_file=pwHy_qVA5b\'); ]]></response>\n</ajax-response>'
I'm not sure what to make of this? is trying to download the CSV from an API call possible? Am I using the wrong call?
TIA.
The following works:
from httpx import Client
from bs4 import BeautifulSoup
data = {
'base_url':'public/reports/real_estate',
'parent_request_id':'4C4ACC20-0155-11ED-9D24-CAB03D8B3709',
'session_id':296334053076598741934874852698924119209,
'app_url':'/tcb/app',
'page_url':'public/reports/real_estate',
'report_name':'Active Certificate Vendors',
'selected_report':623,
'filetype':'csv',
'delimiter':'comma',
'quoting':'on',
'pdf_report_title':'Active Certificate Vendors Report (Certificate Sale Bidders)',
'add_run_by_to_header':'on',
'paper_size':'letter',
'page_orientation':'portrait',
'page_break':'auto',
'break_selector':'bidder_number',
'shade_alternate_rows':'on',
'displayed_columns':'vendor_number|bidder_name|full_name|bidder_number|address_lines|business_telephone|email',
'current_view':'cert_sale_bidders',
'current_display':'data',
'select_view':'cert_sale_bidders',
'last_sort_col':1,
'sbgb_boundary':2,
'search_order_column1':'bidder_number',
'select_display':'data',
'search_order_direction1':'asc',
'rows_per_page':50,
'report_page':1,
'backend':'mysql',
'print_cover_page':0,
'reset_report_name':0,
'preserve_messages':0,
'preserve_backend':0,
'preserve_collapse':0,
'ajax_request':0.6517064905478597,
'cookie_id':1982672363
}
with Client(headers=headers, timeout=60.0, follow_redirects=True) as client:
r = client.post('https://lee.county-taxes.com/tcb/app/public/reports/real_estate/report_results', data=data)
soup = BeautifulSoup(r.text)
profit = soup.select_one('#report_results__results')
print(profit.text)
This returns:
Lee County
Lee County
1
c/o County LandsPO Box 398
countyrevenuetransmittals#leeclerk.org
Venus 1 LLC
Venus 1 LLC
70
P O Box 25177
305-913-3333
Hgoldenberg#g-g-h.com
.....
I am trying to parse the table from https://alreits.com/screener
I have tried this:
main_url = 'https://alreits.com/screener'
r = requests.get(main_url)
df_list = pd.read_html(r.text)
df = df_list[0]
print(df)
but pandas cant find the table.
I have also tried using BeautifulSoup4 but it didnt seem to give better results.
This is the selector: #__next > div.MuiContainer-root.MuiContainer-maxWidthLg > div.MuiBox-root.jss9.Card__CardContainer-feksr6-0.fpbzHQ.ScreenerTable__CardContainer-sc-1c5wxgl-0.GRrTj > div > table > tbody
This is the full xPath: /html/body/div/div[2]/div[2]/div/table/tbody
I am trying to get the Stock symbol (under name),sector,score and market cap. The other data would be nice to have but is not necessary.
Thank You!
I found one JSON url from the dev tool. This is an easy way to extract the table instead of using selenium. Use post request to extract the data.
import requests
headers = {
'authority': 'api.alreits.com:8080',
'sec-ch-ua': '"Google Chrome";v="93", " Not;A Brand";v="99", "Chromium";v="93"',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36',
'sec-ch-ua-platform': '"Windows"',
'content-type': 'application/json',
'accept': '*/*',
'origin': 'https://alreits.com',
'sec-fetch-site': 'same-site',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://alreits.com/',
'accept-language': 'en-US,en;q=0.9',
}
params = (
('page', '0'),
('size', '500'),
('sort', ['marketCap,desc', 'score,desc', 'ffoGrowth,desc']),
)
data = '{"filters":[]}'
response = requests.post('https://api.alreits.com:8080/api/reits/screener', headers=headers, params=params, data=data)
df = pd.DataFrame(response.json())
The code below will return the data you are looking for.
import requests
import pprint
import json
headers = {'content-type': 'application/json',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'}
r = requests.post(
'https://api.alreits.com:8080/api/reits/screener?page=0&size=500&sort=marketCap,desc&sort=score,desc&sort=ffoGrowth,desc',
headers=headers, data=json.dumps({'filters':[]}))
if r.status_code == 200:
pprint.pprint(r.json())
# Now you have the data - do what you want with it
else:
print(r.status_code)