附源码：
import requests
from urllib.parse import urlencode
import re
import os
from requests import codes
from hashlib import md5
from multiprocessing.pool import Pool
def get_page(offset):
headers = {
'cookie': 'tt_webid=6726380411449148935; WEATHER_CITY=%E5%8C%97%E4%BA%AC; __tasessionId=385zzngu11566107488919; tt_webid=6726380411449148935; csrftoken=7bf3e286e8095f9371dc5e2bfab0ed19; s_v_web_id=fb560f45a8b77ca1a01cc1c4abb0e9b1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
'referer': 'https://www.toutiao.com/search/?keyword=%E8%A1%97%E6%8B%8D'
}
params = {
'aid': '24',
'app_name': 'web_search',
'offset': offset,
'format': 'json',
'keyword': '街拍',
'autoload': 'true',
'count': '20',
'en_qc': '1',
'cur_tab': '1',
'from': 'search_tab',
'pd': 'synthesis'
}
base_url = 'https://www.toutiao.com/api/search/content/?'
url = base_url + urlencode(params)
# print(url)
try:
resp = requests.get(url, headers = headers)
if resp.status_code == 200:
return resp.json()
except requests.ConnectionError:
return None
def get_images(json):
if json.get('data'):
data = json.get('data')
for item in data:
if item.get('title') is None:
continue
title = re.sub('[\t]', '', item.get('title'))
images = item.get('image_list')
if images is None:
continue
for image in images:
origin_image = re.sub('list.*?pgc-image', 'large/pgc-image', image.get('url'))
yield {
'image': origin_image,
'title': title
}
def save_image(item):
img_path = 'img' + os.path.sep + item.get('title')
if not os.path.exists(img_path):
os.makedirs(img_path)
try:
resp = requests.get(item.get('image'))
if codes.ok == resp.status_code:
file_path = img_path + os.path.sep + '{file_name}.{file_suffix}'.format(file_name=md5(resp.content).hexdigest(), file_suffix='jpg')
if not os.path.exists(file_path):
with open(file_path, 'wb') as f:
f.write(resp.content)
print('Downloaded image path is %s' % file_path)
else:
print('Already Downloaded', file_path)
except Exception as e:
print(e)
def main(offset):
json = get_page(offset)
for item in get_images(json):
save_image(item)
GROUP_START = 0
GROUP_END = 0
if __name__ == '__main__':
pool = Pool()
groups = ([x * 20 for x in range(GROUP_START, GROUP_END + 1)])
pool.map(main, groups)
pool.close()
pool.join()
爬取效果：
