from urllib.request import urlopen, Request
from bs4 import BeautifulSoup
import re
# 将操作码保存为txt文件
def text_save(filename, data): # filename为写入txt文件的路径,data为要写入数据列表.
file = open(filename, 'w')
for i in range(len(data)):
s = str(data[i]).replace('[', '').replace(']', '') # 去除[],这两行按数据不同,可以选择
s = str(data[i]).replace('(', '').replace(')', '')
s = s.replace("'", '').replace(',', '') + '\n' # 去除单引号,逗号,每行末尾追加换行符
file.write(s)
file.close()
print("保存文件成功")
listall=[]
for i in range(10):
url = 'https://movie.douban.com/top250?start={}&filter='.format(i * 25)
header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'}
ret = Request(url, headers=header)
html = urlopen(ret)
name1s = []
list = []
bs = BeautifulSoup(html, 'html.parser')
numbers = bs.find_all("em", {"class": ""})
names = bs.find_all("span", {"class": "title"})
scores = bs.find_all("span", {"class": "rating_num"})
for name in names:
name = name.get_text()
if name[1] != '/':
name1s.append(name)
for number, name1, score in zip(numbers, name1s, scores):
number = number.get_text()
score = score.get_text()
# print(number, name1, score)
list = number, name1, score
listall.append(list)
# print(listall)
text_save('douban_movie_rankings.txt', listall)
Python爬虫学习之爬取豆瓣电影Top250写入txt文件
最新推荐文章于 2022-02-21 23:46:57 发布