爬取网站:https://maoyan.com/board/4
话不多说,上代码
import requests
import random
from bs4 import BeautifulSoup
import os
global lots_headers
lots_headers = [
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
'Opera/9.25 (Windows NT 5.1; U; en)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0",
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
]
global headers
headers = {'User-Agent': random.choice(lots_headers)}
global url
url = "https://maoyan.com/board/4?offset="
# 保存路径
global savePath
savePath = 'G:\\排行'
global num
num = 1
global testurl
# 保存文件
def savefile(savepath, filename, clean_text, score_text):
global num
if os.path.exists(savePath) is False:
os.mkdir(savePath)
os.chdir(savePath)
try:
f = open(filename, 'a+')
f.write('NO.'+str(num)+' '+clean_text+' 评分:'+score_text+'\n')
f.close()
except Exception as e:
print(e)
def main():
global offset
offset = 0
global num
try:
while offset < 100:
testurl = url + str(offset)
res = requests.get(testurl, headers=headers)
soup = BeautifulSoup(res.text, 'html.parser')
name = soup.find_all('div', class_='movie-item-info')
score = soup.find_all('div', class_='movie-item-number score-num')
filename = '猫眼电影排行榜Top100.txt'
global i
i = 0
while i <= 9:
print("第"+str(num)+"名:"" 评分:"+score[i].text.replace('\n', ' '))
clean_text = ' '.join(name[i].text.split())
print(clean_text)
# 文件写入
savefile(savePath, filename, clean_text, score[i].text.replace('\n', ' '))
num = num + 1
i = i + 1
offset = offset + 10
print('爬取结束')
except Exception as e:
print(e)
if __name__ == '__main__':
main()
此程序简单易懂,有问题请留言。(大佬勿喷,我是个可怜的小白)