（1）抓取今日头条街拍图片
（2）分析今日头条街拍图片结构
keyword: 街拍
pd: atlas
dvpf: pc
aid: 4916
page_num: 1
search_json: {"from_search_id":"20220104115420010212192151532e8188","origin_keyword":"街拍","image_keyword":"街拍"}
rawjson: 1
search_id: 202201041159040101501341671a4749c4
可以找到规律，page_num从1开始累加，其他参数不变
（3）按功能不同编写不同方法组织代码
获取网页json格式数据
def get_page(page_num):
global headers
headers = {
'host': 'so.toutiao.com',
#'referer': 'https://so.toutiao.com/search?keyword=%e8%a1%97%e6%8b%8d&pd=atlas&dvpf=pc&aid=4916&page_num=0&search_json={%22from_search_id%22:%22202112272022060101510440283ee83d67%22,%22origin_keyword%22:%22%e8%a1%97%e6%8b%8d%22,%22image_keyword%22:%22%e8%a1%97%e6%8b%8d%22}',
'user-agent': 'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/86.0.4240.198 safari/537.36',
'x-requested-with': 'xmlhttprequest',
'cookie': 'mstoken=s0dfbkz9hmylogyd3_qjhhxgrm38qtyoitnknb0t_oavfbvxuyv1jz0tt5hlgswsfmzlfd6c2lonm_5tomuqxvxjen7cixm2agwbhhrykjhg; _s_dpr=1.5; _s_ipad=0; monitor_web_id=7046351002275317255; ttwid=1%7c0ydwalndiispik3cvvhwv25u8drq3qaj08e8qoapxhs%7c1640607595%7c720e971d353416921df127996ed708931b4ae28a0a8691a5466347697e581ce8; _s_win_wh=262_623'
}
params = {
'keyword': '街拍',
'pd': 'atlas',
'dvpf': 'pc',
'aid': '4916',
'page_num': page_num,
'search_json': '%7b%22from_search_id%22%3a%22202112272022060101510440283ee83d67%22%2c%22origin_keyword%22%3a%22%e8%a1%97%e6%8b%8d%22%2c%22image_keyword%22%3a%22%e8%a1%97%e6%8b%8d%22%7d',
'rawjson': 1,
'search_id': '2021122721183101015104402851e3883d'
}
url = 'https://so.toutiao.com/search?' + urlencode(params)
print(url)
try:
response=requests.get(url,headers=headers,params=params)
if response.status_code == 200:
#if response.content:
#print(response.json())
return response.json()
except requests.connectionerror:
return none
从json格式数据提取街拍图片
def get_images(json):
images = json.get('rawdata').get('data')
for image in images:
link = image.get('img_url')
yield link
将街拍图片以其md5码命名并保存图片
实现一个保存图片的方法 save_image()，其中 item 就是前面 get_images() 方法返回的一个字典。在该方法中，首先根据 item 的 title 来创建文件夹，然后请求这个图片链接，获取图片的二进制数据，以二进制的形式写入文件。图片的名称可以使用其内容的 md5 值，这样可以去除重复。相关代码如下：
def save_image(link):
data = requests.get(link).content
with open(f'./image/{md5(data).hexdigest()}.jpg', 'wb')as f:#使用data的md5码作为图片名
f.write(data)
main()调用其他函数
def main(page_num):
json = get_page(page_num)
for link in get_images(json):
#print(link)
save_image(link)
（4）抓取20page今日头条街拍图片数据
这里定义了分页的起始页数和终止页数，分别为 group_start 和 group_end，还利用了多线程的线程池，调用其 map() 方法实现多线程下载。
if __name__ == '__main__':
group_start = 1
group_end = 20
pool = pool()
groups = ([x for x in range(group_start, group_end + 1)])
#print(groups)
pool.map(main, groups)
pool.close()
pool.join()
import requests
from urllib.parse import urlencode
from hashlib import md5
from multiprocessing.pool import pool
def get_page(page_num):
global headers
headers = {
'host': 'so.toutiao.com',
#'referer': 'https://so.toutiao.com/search?keyword=%e8%a1%97%e6%8b%8d&pd=atlas&dvpf=pc&aid=4916&page_num=0&search_json={%22from_search_id%22:%22202112272022060101510440283ee83d67%22,%22origin_keyword%22:%22%e8%a1%97%e6%8b%8d%22,%22image_keyword%22:%22%e8%a1%97%e6%8b%8d%22}',
'user-agent': 'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/86.0.4240.198 safari/537.36',
'x-requested-with': 'xmlhttprequest',
'cookie': 'mstoken=s0dfbkz9hmylogyd3_qjhhxgrm38qtyoitnknb0t_oavfbvxuyv1jz0tt5hlgswsfmzlfd6c2lonm_5tomuqxvxjen7cixm2agwbhhrykjhg; _s_dpr=1.5; _s_ipad=0; monitor_web_id=7046351002275317255; ttwid=1%7c0ydwalndiispik3cvvhwv25u8drq3qaj08e8qoapxhs%7c1640607595%7c720e971d353416921df127996ed708931b4ae28a0a8691a5466347697e581ce8; _s_win_wh=262_623'
}
params = {
'keyword': '街拍',
'pd': 'atlas',
'dvpf': 'pc',
'aid': '4916',
'page_num': page_num,
'search_json': '%7b%22from_search_id%22%3a%22202112272022060101510440283ee83d67%22%2c%22origin_keyword%22%3a%22%e8%a1%97%e6%8b%8d%22%2c%22image_keyword%22%3a%22%e8%a1%97%e6%8b%8d%22%7d',
'rawjson': 1,
'search_id': '2021122721183101015104402851e3883d'
}
url = 'https://so.toutiao.com/search?' + urlencode(params)
print(url)
try:
response=requests.get(url,headers=headers,params=params)
if response.status_code == 200:
#if response.content:
#print(response.json())
return response.json()
except requests.connectionerror:
return none
def get_images(json):
images = json.get('rawdata').get('data')
for image in images:
link = image.get('img_url')
yield link
def save_image(link):
data = requests.get(link).content
with open(f'./image/{md5(data).hexdigest()}.jpg', 'wb')as f:#使用data的md5码作为图片名
f.write(data)
def main(page_num):
json = get_page(page_num)
for link in get_images(json):
#print(link)
save_image(link)
if __name__ == '__main__':
group_start = 1
group_end = 20
pool = pool()
groups = ([x for x in range(group_start, group_end + 1)])
#print(groups)
pool.map(main, groups)
pool.close()
pool.join()
到此这篇关于python抓取今日头条街拍图片数据的文章就介绍到这了,更多相关python抓取今日头条图片内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com！
黄山市民网：https://www.huangshanshimin.com/
