icobench_stuff

from bs4 import BeautifulSoup
import requests
import html5lib
import lxml
import urllib3

NUMBERS = ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28", "29", "30", "31", "32", "33", "34", "35", "36", "37", "38", "39", "40", "41", "42", "43", "44", "45", "46", "47", "48", "49", "50", "51", "52", "53", "54", "55", "56", "57", "58", "59"]
ICOBENCH_URL = "https://icobench.com/icos?page={num}"

#loop for getting all the ongoing, past and future ico links
projects_names = []
for num in NUMBERS:
    res = requests.get(ICOBENCH_URL.format(num=num))
    if res.status_code == 200:
        tree = BeautifulSoup(res.text, "lxml")
        for div in tree.find_all(class_="content"): #список всех блоков класса с инфо по ico
            projects_names.append(div.a.get('href'))
    else:
        print("Error in page num" + num)
        
        
len(projects_names)

ICOBENCH_ICO_URL = "https://icobench.com/{project}"

#ICO_info: луп, который выгружает название, дату и размер сборов
ICO_info = {}
for project in projects_names:
    res = requests.get(ICOBENCH_ICO_URL.format(project=project))
    if res.status_code == 200:
        tree = BeautifulSoup(res.text, "html5lib")
        for project in tree.find_all("div", class_="name"):
            if not (project.h1):
                continue
            name = project.h1.string
            ICO_info['name'] = name
        for project in tree.find_all("div", class_="col_2 expand"):
            if not (project.small):
                continue
            date = project.small.string
            ICO_info['date'] = date
            
        for project in tree.find_all("div", class_="raised"):
            raised = project.string
            ICO_info['raised'] = raised

        financial_data_node = tree.find("div", class_="financial_data") 
        for data_row_node in financial_data_node.find_all("div", class_="data_row"):    
            kind_node, data_node = data_row_node.find_all('div', class_='col_2')
            kind, data = kind_node.text.strip().lower(), data_node.text.strip()
            ICO_info[kind] = data

    else:
        raise Exception("Error")