ddtt练习

# https://www.dytt89.com/
import requests
from lxml import etree
import os
import csv
import re


source = requests.get('https://www.dytt89.com/')
source.encoding = 'gb2312'

# os.mkdir('b')
# print(source.text)

html = etree.HTML(source.text)
lists = html.xpath('//div[@class="co_content222"]/ul/li')

s = []
for i in lists:
    movie_url = i.xpath('./a/@href')[0]
    if 'https:' in movie_url:
        continue
    try:
        movie_name = i.xpath('./a/text()')[0]
        # print(movie_name)
    except Exception as e:
        print(e)
        movie_name = i.xpath('./a/@title')[0]

    # print(movie_name)
    movie_url = 'https://www.dytt89.com' + movie_url
    print(movie_url)
    infos_source = requests.get(url=movie_url)
    infos_source.encoding = 'gb2312'
    # print(infos_source.text)
    obj = re.compile(r'<br />◎译　　名　(?P<yiming>.*?)<br />◎片　　名　(?P<name>.*?)'
                     '<br />◎年　　代　(?P<year>.*?)<br />◎产　　地　(?P<area>.*?)<br />◎类　　别　(?P<type>.*?)<br />',re.S)

    infos = obj.finditer(infos_source.text)

    if not infos:
        print('没有爪刀')
    for i in infos:
        print(11111, i.group())
        print(i.group('yiming'))
        print(i.group('name'))
        print(i.group('year'))
        print(i.group('area'))
        print(i.group('type'))

    s.append([movie_name, movie_url])



with open('ddtt.csv', 'w', encoding='utf8', newline='') as f:
    writer = csv.writer(f)
    writer.writerows(s)

    # print('写入:', movie_name, movie_url)
    # print('over!!')