Added code to replace <br/> by \n in positions

This commit is contained in:
TheDevKiller 2018-11-07 23:32:46 +01:00
parent 1337d3ce8a
commit b3788fe34d

View File

@ -7,12 +7,14 @@ Created on Mon Nov 5 20:55:36 2018
""" """
import requests import requests
import re
def runfetch(url): def runfetch(url):
session=requests.Session() session=requests.Session()
req1=session.get(url) req1=session.get(url) # Get the source code
text=req1.text.split('\n') text=req1.text.split('\n')
# Parse the HTML source code
text=['\n'.join(row.split('\n')[:row.split('\n').index("</tr>"):]) for row in '\n'.join(text[text.index('<br/>ANNEXES<br/>ANNEXE I</p>'):text.index('<div style="margin-top: 30px; margin-bottom:20px;" id="JORFSCTA000037493059" class="titreSection">Annexe </div>'):]).split('<tr>')[2::]] text=['\n'.join(row.split('\n')[:row.split('\n').index("</tr>"):]) for row in '\n'.join(text[text.index('<br/>ANNEXES<br/>ANNEXE I</p>'):text.index('<div style="margin-top: 30px; margin-bottom:20px;" id="JORFSCTA000037493059" class="titreSection">Annexe </div>'):]).split('<tr>')[2::]]
diclist=[] diclist=[]
for row in text: for row in text:
@ -23,8 +25,11 @@ def runfetch(url):
if __name__ == '__main__': if __name__ == '__main__':
diclist=runfetch('https://www.legifrance.gouv.fr/eli/arrete/2018/10/12/PRMD1824595A/jo/texte') diclist=runfetch('https://www.legifrance.gouv.fr/eli/arrete/2018/10/12/PRMD1824595A/jo/texte') # Fetch all the data from a french article
url='https://www.legifrance.gouv.fr/eli/arrete/2018/10/12/PRMD1824595A/jo/texte' url='https://www.legifrance.gouv.fr/eli/arrete/2018/10/12/PRMD1824595A/jo/texte'
for index, zone in enumerate(diclist):
for element in zone:
diclist[index][element] = re.sub("<br.{0,2}>", "\n", diclist[index][element]) # Replace <br>, <br /> and <br/> by \n
# Print the dict # Print the dict
print("===== Dict =====") print("===== Dict =====")
for index, zone in enumerate(diclist): for index, zone in enumerate(diclist):