博客园编程语言文章数量 爬虫

cnblogs.py

import requests
from bs4 import BeautifulSoup

base_url = 'https://zzk.cnblogs.com/s/blogpost'
cookies = dict(
    ZzkNoRobotCookie=
    'CfDJ8KlpyPucjmhMuZTmH8oiYTOsZWLqcxSx0sRuNdfc35P334ttmwTqPekgb1OOGtp_JeXby7PZgQla4HC63Y3_nnWwF8kvdklA71DbLOQ2ADfziUqy4BkuXQUgJEB4y2kj6w'
)

languages = [
    'Python', '.NET', 'JavaScript', 'C++', 'Java', 'Erlang', 'Scala', 'PHP',
    'Haskell', 'Lisp', 'C#', 'Julia', 'Nodejs'
]

for lang in languages:
    r = requests.get(base_url, params={'w': lang}, cookies=cookies)
    if not r.status_code == 200:
        print(f'Error code: {r.status_code}')
        continue
    # print(r.text)
    soup = BeautifulSoup(r.text)
    try:
        print(f'{lang}: {soup.find(id="CountOfResults").get_text()}')
    except:
        print(r.url)