python 批量Alexa网站排名

Posted 2021-05-08

import requests
import re

sites=  [("url","sitename"),
            ("url","sitename"),
            ("url","sitename")
            ]

regex = re.compile(r".*POPULARITY URL=.+ TEXT=\"(\d+)\" SOURCE.*")

ranked = []
nonranked = []

def get_rank(site):
    s = requests.get("http://data.alexa.com/data?cli=100&url=" + site)
    ma = regex.search(s.text)
    if ma:
          return int(ma.group(1))
    return None

# Go through all the sites
for site in sites:
    rank = get_rank(site[0])
    if rank is not None:
        ranked.append((site[0], site[1], rank))
    else:
        nonranked.append((site[0], site[1], rank))