2
我有波纹管代码:熊猫导出为CSV
from xlsxwriter import Workbook
import os,shutil
import requests
import pandas
from bs4 import BeautifulSoup
MAX_RETRIES = 20
base_url='https://pagellapolitica.it/politici/sfoggio/9/matteo-renzi?page='
for page in range(1,32,1):
l=[]
session = requests.Session()
adapter = requests.adapters.HTTPAdapter(max_retries=MAX_RETRIES)
session.mount('https://', adapter)
session.mount('http://', adapter)
site=(base_url+str(page)+".html")
# print(site)
c=session.get(site)
r=c.content
soup=BeautifulSoup(r,'html.parser')
all=soup.find_all("div",{"class":"clearfix"})
for d in all:
links=d.find_all("a")
len(links)
l=[]
# workbook = Workbook('bbb.xlsx')
# worksheet = workbook.add_worksheet()
# row +=0
# worksheet.write(row,0,'Link')
# worksheet.write(row,1,'Name ')
# row+=1
for a in links[5:17]:
d={}
href=(a["href"])
basic_url=('https://pagellapolitica.it/')
site =basic_url + href
#print(site)
c=requests.get(site)
r=c.content
soup=BeautifulSoup(r,'html.parser')
Name=soup.find("h3",{"class":"pull-left"}).text
Fact_checking=soup.find("label",{"class":"verdict-analisi"}).text
quote=soup.find("div",{"class":"col-xs-12 col-sm-6 col-smm-6 col-md-5 col-lg-5"}).text
all=soup.find_all("span",{"class":"item"})
Topic=all[0].text
Date=all[2].text
a=all[3].find("a",{"class":"" ""})
Link=a["href"]
Text=soup.find("div",{"class":"col-xs-12 col-md-12 col-lg-12"}).text
d["Name"]=Name
d["Fact_checking"]=Fact_checking
d["Quote"]=quote
d["Economic_topic"]=Topic
d["Date"]=Date
d["Link"]=Link
d["Text"]=Text
l.append(d)
df=pandas.DataFrame(l)
df.to_csv("outing.csv")
,当我在CSV导出数据我只得到6行results.When我做印刷(DF)和打印(L)的问题它会打印列表中的所有数据,但是当我检查len(l)时,我只能得到6的长度。任何想法为什么会发生这种情况? 提前谢谢!
您可以在问题的底部添加'df.info()'输出。请务必在添加之前将其格式化为可读。 – Nitred
你在内循环的每次迭代中覆盖你的CSV文件... – MaxU
在循环的外部移动'df = pandas.DataFrame(l)'和'df.to_csv(“outing.csv”)' –