Python3 靜態爬蟲

開始

程式碼

import urllib.request
url = "https://disp.cc/b/PttHot" # The website url you want to access
response = urllib.request.urlopen(url)
data = response.read()
text = data.decode('utf-8-sig')
print(text)

py -3 main.py

from bs4 import BeautifulSoup
soup = BeautifulSoup(text, "lxml") # parse

span class = 'L34 nowrap listTitle', id = 'titleXXXXX'

span class = 'list-num'

soup = BeautifulSoup(text, "lxml") # parse
listIdxs = soup.body.find_all('span', attrs={'class':'list-num'}) # get all list

targets = soup.body.find_all('span', attrs={'class':'L34 nowrap listTitle', 'id':'title52419'})

import urllib.request
from bs4 import BeautifulSoup

def downLoad():
url = "https://disp.cc/b/PttHot"

response = urllib.request.urlopen(url)
data = response.read() # a `bytes` object
text = data.decode('utf-8-sig') # a `str`; this step can't be used if data is binary
return text

print("downloading.. ")
print("=============================")
text = downLoad()
soup = BeautifulSoup(text, "lxml") # parse
listIdxs = soup.body.find_all('span', attrs={'class':'list-num'}) # get all list
for listIdx in listIdxs:
targets = soup.body.find_all('span', attrs={'class':'L34 nowrap listTitle', 'id':'title'+listIdx.text})
for ta in targets:
print(ta.text)

執行結果

參考