Objective
-> Usage of Beautiful soup package + cfscrape to bypass anti bot systems
In [2]:
import cfscrape
from bs4 import BeautifulSoup
scraper = cfscrape.create_scraper() # returns a CloudflareScraper instance
# Or: scraper = cfscrape.CloudflareScraper() # CloudflareScraper inherits from requests.Session
r= scraper.get("https://etherchain.org/contracts").content # => "<!DOCTYPE html><html><head>..."
soup = BeautifulSoup(r)
table = soup.find('table', {'class': 'table table-condensed'})
rows = table.find_all('tr')
print('Accounts :')
print('--------')
for row in rows:
print row.find('a').get('href')[9:] ,row.find('a').contents[0]
In [3]:
r2= scraper.get("https://etherchain.org/accounts/10").content # => "<!DOCTYPE html><html><head>..."
soup = BeautifulSoup(r2)
table = soup.find('table', {'class': 'table table-condensed'})
rows = table.find_all('tr')
for i in range(1,len(rows)):
print rows[i].find_all('td')[0].find('a').contents[0], rows[i].find_all('td')[2].contents[0]