Last active
August 26, 2020 22:32
-
-
Save elazarg/87566015c436c43f3a683725b89e5371 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
import requests | |
from isoweek import Week | |
def fetch_table(year, week): | |
date = Week(year, week).sunday().strftime("%d/%m/%Y") | |
url = 'http://212.150.52.211/scripts/rating10.asp' | |
response = requests.post(url, data={ | |
'audience': '1', | |
'week': date, | |
'date_selector': 'weekly', | |
}, headers={ | |
'Content-Type': 'application/x-www-form-urlencoded' | |
}) | |
return response.content | |
def reverse_hebrew(s): | |
return ' '.join(reversed([ | |
x[::-1].replace('ה-08', 'ה-80') if any(c in x for c in 'אבגדהוזחטיכלמנסעפצקרשת') else x | |
for x in s.split() | |
])) | |
def parse(html): | |
bs = BeautifulSoup(html, features="lxml") | |
for tr in bs.find_all('tr'): | |
tds = tr.find_all('td') | |
if len(tds) != 9: | |
continue | |
values = [reverse_hebrew(x.get_text().replace('\n', '').strip()) for x in tds] | |
percent, thousands, rating, duration, day, date, channel, name, rank = values | |
if not rank.isdigit(): | |
continue | |
yield (rank, name, channel, date, day, duration, rating, thousands, percent) | |
if __name__ == '__main__': | |
with open('rating.csv', 'w', encoding='utf8') as f: | |
for year in range(2008, 2020): | |
numweeks = 52 if year < 2020 else 34 | |
for week in range(numweeks): | |
print(year, week, end='\r', flush=True) | |
html = fetch_table(year, week) | |
for rank, *row in parse(html): | |
print(year, week, *row, sep=',', file=f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment