爬虫记录(持续更新)

（1）

code:获取图片path及图片下面的名字
通过find_all("img)获取所有path url
from bs4 import BeautifulSoup
import requests
url = "https://car.autohome.com.cn//pic/series/5605-53.html#pvareaid=2042220"
source = requests.get(url).text
soup = BeautifulSoup(source,'lxml')
details= soup.find_all("img") # 找所有的img
for i in details:
    print("======================================================")
    print(i)
    name = str(i).rsplit("alt=")[1].rsplit(" src=")[0][1:-1]
    pic_path = str(i).rsplit("src=")[1][1:].rsplit(" title=")[0][:-1]
    pic_url = "https://" + pic_path
    print(pic_url)

print:
======================================================
<img alt="2021款 R" src="//car2.autoimg.cn/cardfs/product/g24/M0A/00/40/240x180_0_q95_c42_autohomecar__Chtk3WCU5BWAYilJAB_CUi1NNDw970.jpg" title="2021款 R"/>
https:car2.autoimg.cn/cardfs/product/g24/M0A/00/40/240x180_0_q95_c42_autohomecar__Chtk3WCU5BWAYilJAB_CUi1NNDw970.jpg
======================================================
<img alt="" height="80" sizes="80px" src="//x.autoimg.cn/car/images/loginrb1x.png" srcset="//x.autoimg.cn/car/images/loginrb1x.png
 80w, //x.autoimg.cn/car/images/loginrb2x.png 160w" width="80"/>
https:x.autoimg.cn/car/images/loginrb1x.png" srcset="//x.autoimg.cn/car/images/loginrb1x.png
 80w, //x.autoimg.cn/car/images/loginrb2x.png 160w" width="80"/

网页截图：

2、

code:通过find class_="page",获取text
from bs4 import BeautifulSoup
import requests

url = "https://car.autohome.com.cn//pic/series/5605-53.html#pvareaid=2042220"
source = requests.get(url).text
soup = BeautifulSoup(source,'lxml')
details_page= soup.find(class_="page") #@@@@@
print(details_page.text)  #@@@@@
txt_path = "./url/" + str("fdas") + ".txt"
cou =1
for i in details_page:
    # print(str(i))
    if "href" in str(i) and "class" not in str(i):
        print(i)
        next_page = "https://car.autohome.com.cn/"# + i.title()
        for j in range(10):
            cou += 1
            new_url = url + str(cou)
print:
上一页12345下一页
<a href="/pic/series/5605-53-p2.html">2</a>
<a href="/pic/series/5605-53-p3.html">3</a>
<a href="/pic/series/5605-53-p4.html">4</a>
<a href="/pic/series/5605-53-p5.html">5</a>

3、

from bs4 import BeautifulSoup
import requests

url = "https://car.autohome.com.cn//pic/series/5605-53.html#pvareaid=2042220"
source = requests.get(url).text
soup = BeautifulSoup(source,'lxml')
details_page= soup.find(class_="page") #@@@@@
print(details_page.text)  #@@@@@
txt_path = "./url/" + str("fdas") + ".txt"
cou =1
for i in details_page:
    if "href" in str(i) and "class" not in str(i):
        print(i.contents)  ####
        next_page = "https://car.autohome.com.cn/" #+ i.
        for j in range(10):
            cou += 1
            new_url = url + str(cou)


print():
上一页12345下一页
['2']
['3']
['4']
['5']