python使用re模塊實現(xiàn)爬取豆瓣Top250電影

import re
import requests

# 爬蟲三部曲：
# 1.獲取請求
def get_data(url, headers):
  response = requests.get(url, headers=headers)
  # 如果爬取的是html文本就是用.text方法獲取文本數(shù)據(jù)，如果爬取的是音視頻就用.content方法獲取二進(jìn)制流數(shù)據(jù)
  # print(response.text)  # 獲取相應(yīng)文本，比如html代碼
  return response.text

# 2.解析數(shù)據(jù)
def parser_data(text):
  # re.findall("正則表達(dá)式", "過濾的文本", re.S) # 匹配模式：re.S 全局模式
  data = re.findall(
    '<div class="item">.*&#63;<a href="(.*&#63;)" rel="external nofollow" >.*&#63;<span class="title">(.*&#63;)</span>.*&#63;<span class="rating_num" property="v:average">(.*&#63;)</span>.*&#63;<span>(.*&#63;)人評價</span>', text, re.S)
  for move_info in data:
    yield move_info

# 3.保存數(shù)據(jù)
def save_data(res_list_iter):
  with open("豆瓣TOP250.txt", "a", encoding="utf-8") as f:
    for i in res_list_iter:
      move_page, move_title, move_score, move_evaluation = i
      # print(move_page, move_title, move_score, move_evaluation)
      str1 = f"電影名字：《{move_title}》  電影評分：{move_score}  電影評價：{move_evaluation}  電影詳情頁：{move_page}\n"
      f.write(str1)

# 使用請求頭請求數(shù)據(jù)
headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 \
  Safari/537.36'
}
n = 0
# 獲取10個鏈接
for i in range(10):
  url = f"https://movie.douban.com/top250&#63;start={n}&filter=="
  n += 25
  text = get_data(url, headers)
  res_list_iter = parser_data(text)
  save_data(res_list_iter)