import requests
from lxml import html
# 創(chuàng)建 session 對象。這個對象會保存所有的登錄會話請求。
session_requests = requests.session()
# 提取在登錄時所使用的 csrf 標記
login_url = "https://bitbucket.org/account/signin/?next=/"
result = session_requests.get(login_url)
tree = html.fromstring(result.text)
authenticity_token = list(set(tree.xpath("http://input[@name='csrfmiddlewaretoken']/@value")))[0]
payload = {
  "username": "<你的用戶名>",
  "password": "<你的密碼>",
  "csrfmiddlewaretoken": authenticity_token # 在源代碼中，有一個名為 “csrfmiddlewaretoken” 的隱藏輸入標簽。
}
# 執(zhí)行登錄
result = session_requests.post(
  login_url,
  data = payload,
  headers = dict(referer=login_url)
)
# 已經(jīng)登錄成功了，然后從 bitbucket dashboard 頁面上爬取內(nèi)容。
url = 'https://bitbucket.org/dashboard/overview'
result = session_requests.get(
  url,
  headers = dict(referer = url)
)
# 測試爬取的內(nèi)容
tree = html.fromstring(result.content)
bucket_elems = tree.findall(".//span[@class='repo-name']/")
bucket_names = [bucket.text_content.replace("n", "").strip() for bucket in bucket_elems]
print(bucket_names)